Merge remote-tracking branch 'origin/dev/k3.3-rc1-iommu' into android-tegra-nv-3.1

Change-Id: I9001bb291779f107bbcb593d48f9f0f734074d0e

10 files changed, 75 insertions, 115 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a47bb22657f..b8cd5448b0e1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -130,7 +130,7 @@ config SBUS
 	bool
 
 config NEED_DMA_MAP_STATE
-       def_bool (X86_64 || DMAR || DMA_API_DEBUG)
+       def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG)
 
 config NEED_SG_DMA_LENGTH
 	def_bool y
@@ -220,7 +220,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 
 config HAVE_INTEL_TXT
 	def_bool y
-	depends on EXPERIMENTAL && DMAR && ACPI
+	depends on EXPERIMENTAL && INTEL_IOMMU && ACPI
 
 config X86_32_SMP
 	def_bool y
@@ -287,7 +287,7 @@ config SMP
 
 config X86_X2APIC
 	bool "Support x2apic"
-	depends on X86_LOCAL_APIC && X86_64 && INTR_REMAP
+	depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
 	---help---
 	  This enables x2apic support on CPUs that have this feature.
 
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 22a0dc8e51dd..058a35b8286c 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -67,8 +67,8 @@ CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_X86_ACPI_CPUFREQ=y
 CONFIG_PCI_MMCONFIG=y
-CONFIG_DMAR=y
-# CONFIG_DMAR_DEFAULT_ON is not set
+CONFIG_INTEL_IOMMU=y
+# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCCARD=y
 CONFIG_YENTA=y
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 029f230ab637..63a2a03d7d51 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,7 +8,7 @@ struct dev_archdata {
 #ifdef CONFIG_X86_64
 struct dma_map_ops *dma_ops;
 #endif
-#if defined(CONFIG_DMAR) || defined(CONFIG_AMD_IOMMU)
+#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
 	void *iommu; /* hook for IOMMU specific extension */
 #endif
 };
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 09199052060f..eb92a6ed2be7 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -119,7 +119,7 @@ struct irq_cfg {
 	cpumask_var_t		old_domain;
 	u8			vector;
 	u8			move_in_progress : 1;
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
 	struct irq_2_iommu	irq_2_iommu;
 #endif
 };
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 345c99cef152..dffc38ee6255 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -5,6 +5,7 @@ extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int iommu_pass_through;
+extern int iommu_group_mf;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 1c23360fb2d8..47d99934580f 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,7 +3,8 @@
 
 #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip);
 static inline void prepare_irte(struct irte *irte, int vector,
 			        unsigned int dest)
 {
@@ -36,6 +37,9 @@ static inline bool irq_remapped(struct irq_cfg *cfg)
 {
 	return false;
 }
+static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+}
 #endif
 
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 52fa56399a50..a2fd72e0ab35 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1437,27 +1437,21 @@ void enable_x2apic(void)
 
 int __init enable_IR(void)
 {
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
 	if (!intr_remapping_supported()) {
 		pr_debug("intr-remapping not supported\n");
-		return 0;
+		return -1;
 	}
 
 	if (!x2apic_preenabled && skip_ioapic_setup) {
 		pr_info("Skipped enabling intr-remap because of skipping "
 			"io-apic setup\n");
-		return 0;
+		return -1;
 	}
 
-	if (enable_intr_remapping(x2apic_supported()))
-		return 0;
-
-	pr_info("Enabled Interrupt-remapping\n");
-
-	return 1;
-
+	return enable_intr_remapping();
 #endif
-	return 0;
+	return -1;
 }
 
 void __init enable_IR_x2apic(void)
@@ -1481,11 +1475,11 @@ void __init enable_IR_x2apic(void)
 	mask_ioapic_entries();
 
 	if (dmar_table_init_ret)
-		ret = 0;
+		ret = -1;
 	else
 		ret = enable_IR();
 
-	if (!ret) {
+	if (ret < 0) {
 		/* IR is required if there is APIC ID > 255 even when running
 		 * under KVM
 		 */
@@ -1499,6 +1493,9 @@ void __init enable_IR_x2apic(void)
 		x2apic_force_phys();
 	}
 
+	if (ret == IRQ_REMAP_XAPIC_MODE)
+		goto nox2apic;
+
 	x2apic_enabled = 1;
 
 	if (x2apic_supported() && !x2apic_mode) {
@@ -1508,19 +1505,21 @@ void __init enable_IR_x2apic(void)
 	}
 
 nox2apic:
-	if (!ret) /* IR enabling failed */
+	if (ret < 0) /* IR enabling failed */
 		restore_ioapic_entries();
 	legacy_pic->restore_mask();
 	local_irq_restore(flags);
 
 out:
-	if (x2apic_enabled)
+	if (x2apic_enabled || !x2apic_supported())
 		return;
 
 	if (x2apic_preenabled)
 		panic("x2apic: enabled by BIOS but kernel init failed.");
-	else if (cpu_has_x2apic)
-		pr_info("Not enabling x2apic, Intr-remapping init failed.\n");
+	else if (ret == IRQ_REMAP_XAPIC_MODE)
+		pr_info("x2apic not enabled, IRQ remapping is in xapic mode\n");
+	else if (ret < 0)
+		pr_info("x2apic not enabled, IRQ remapping init failed\n");
 }
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8eb863e27ea6..620da6fed6b7 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1202,7 +1202,6 @@ void __setup_vector_irq(int cpu)
 }
 
 static struct irq_chip ioapic_chip;
-static struct irq_chip ir_ioapic_chip;
 
 #ifdef CONFIG_X86_32
 static inline int IO_APIC_irq_trigger(int irq)
@@ -1246,7 +1245,7 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
 
 	if (irq_remapped(cfg)) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-		chip = &ir_ioapic_chip;
+		irq_remap_modify_chip_defaults(chip);
 		fasteoi = trigger != 0;
 	}
 
@@ -2255,7 +2254,7 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
 
 /*
  * Migrate the IO-APIC irq in the presence of intr-remapping.
@@ -2267,6 +2266,9 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
  * updated vector information), by using a virtual vector (io-apic pin number).
  * Real vector that is used for interrupting cpu will be coming from
  * the interrupt-remapping table entry.
+ *
+ * As the migration is a simple atomic update of IRTE, the same mechanism
+ * is used to migrate MSI irq's in the presence of interrupt-remapping.
  */
 static int
 ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
@@ -2291,10 +2293,16 @@ ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	irte.dest_id = IRTE_DEST(dest);
 
 	/*
-	 * Modified the IRTE and flushes the Interrupt entry cache.
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
 	 */
 	modify_irte(irq, &irte);
 
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
 
@@ -2552,7 +2560,7 @@ static void ack_apic_level(struct irq_data *data)
 	}
 }
 
-#ifdef CONFIG_INTR_REMAP
+#ifdef CONFIG_IRQ_REMAP
 static void ir_ack_apic_edge(struct irq_data *data)
 {
 	ack_APIC_irq();
@@ -2563,7 +2571,23 @@ static void ir_ack_apic_level(struct irq_data *data)
 	ack_APIC_irq();
 	eoi_ioapic_irq(data->irq, data->chip_data);
 }
-#endif /* CONFIG_INTR_REMAP */
+
+static void ir_print_prefix(struct irq_data *data, struct seq_file *p)
+{
+	seq_printf(p, " IR-%s", data->chip->name);
+}
+
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+	chip->irq_print_chip = ir_print_prefix;
+	chip->irq_ack = ir_ack_apic_edge;
+	chip->irq_eoi = ir_ack_apic_level;
+
+#ifdef CONFIG_SMP
+	chip->irq_set_affinity = ir_ioapic_set_affinity;
+#endif
+}
+#endif /* CONFIG_IRQ_REMAP */
 
 static struct irq_chip ioapic_chip __read_mostly = {
 	.name			= "IO-APIC",
@@ -2578,21 +2602,6 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
-static struct irq_chip ir_ioapic_chip __read_mostly = {
-	.name			= "IR-IO-APIC",
-	.irq_startup		= startup_ioapic_irq,
-	.irq_mask		= mask_ioapic_irq,
-	.irq_unmask		= unmask_ioapic_irq,
-#ifdef CONFIG_INTR_REMAP
-	.irq_ack		= ir_ack_apic_edge,
-	.irq_eoi		= ir_ack_apic_level,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= ir_ioapic_set_affinity,
-#endif
-#endif
-	.irq_retrigger		= ioapic_retrigger_irq,
-};
-
 static inline void init_IO_APIC_traps(void)
 {
 	struct irq_cfg *cfg;
@@ -3144,45 +3153,6 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 
 	return 0;
 }
-#ifdef CONFIG_INTR_REMAP
-/*
- * Migrate the MSI irq to another cpumask. This migration is
- * done in the process context using interrupt-remapping hardware.
- */
-static int
-ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		    bool force)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	unsigned int dest, irq = data->irq;
-	struct irte irte;
-
-	if (get_irte(irq, &irte))
-		return -1;
-
-	if (__ioapic_set_affinity(data, mask, &dest))
-		return -1;
-
-	irte.vector = cfg->vector;
-	irte.dest_id = IRTE_DEST(dest);
-
-	/*
-	 * atomically update the IRTE with the new destination and vector.
-	 */
-	modify_irte(irq, &irte);
-
-	/*
-	 * After this point, all the interrupts will start arriving
-	 * at the new destination. So, time to cleanup the previous
-	 * vector allocation.
-	 */
-	if (cfg->move_in_progress)
-		send_cleanup_vector(cfg);
-
-	return 0;
-}
-
-#endif
 #endif /* CONFIG_SMP */
 
 /*
@@ -3200,19 +3170,6 @@ static struct irq_chip msi_chip = {
 	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
-static struct irq_chip msi_ir_chip = {
-	.name			= "IR-PCI-MSI",
-	.irq_unmask		= unmask_msi_irq,
-	.irq_mask		= mask_msi_irq,
-#ifdef CONFIG_INTR_REMAP
-	.irq_ack		= ir_ack_apic_edge,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= ir_msi_set_affinity,
-#endif
-#endif
-	.irq_retrigger		= ioapic_retrigger_irq,
-};
-
 /*
  * Map the PCI dev to the corresponding remapping hardware unit
  * and allocate 'nvec' consecutive interrupt-remapping table entries
@@ -3255,7 +3212,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 
 	if (irq_remapped(irq_get_chip_data(irq))) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-		chip = &msi_ir_chip;
+		irq_remap_modify_chip_defaults(chip);
 	}
 
 	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
@@ -3328,7 +3285,7 @@ void native_teardown_msi_irq(unsigned int irq)
 	destroy_irq(irq);
 }
 
-#if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
+#ifdef CONFIG_DMAR_TABLE
 #ifdef CONFIG_SMP
 static int
 dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
@@ -3409,19 +3366,6 @@ static int hpet_msi_set_affinity(struct irq_data *data,
 
 #endif /* CONFIG_SMP */
 
-static struct irq_chip ir_hpet_msi_type = {
-	.name			= "IR-HPET_MSI",
-	.irq_unmask		= hpet_msi_unmask,
-	.irq_mask		= hpet_msi_mask,
-#ifdef CONFIG_INTR_REMAP
-	.irq_ack		= ir_ack_apic_edge,
-#ifdef CONFIG_SMP
-	.irq_set_affinity	= ir_msi_set_affinity,
-#endif
-#endif
-	.irq_retrigger		= ioapic_retrigger_irq,
-};
-
 static struct irq_chip hpet_msi_type = {
 	.name = "HPET_MSI",
 	.irq_unmask = hpet_msi_unmask,
@@ -3458,7 +3402,7 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 	hpet_msi_write(irq_get_handler_data(irq), &msg);
 	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 	if (irq_remapped(irq_get_chip_data(irq)))
-		chip = &ir_hpet_msi_type;
+		irq_remap_modify_chip_defaults(chip);
 
 	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
 	return 0;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index b49d00da2aed..3b730fb13855 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -44,6 +44,15 @@ int iommu_detected __read_mostly = 0;
  */
 int iommu_pass_through __read_mostly;
 
+/*
+ * Group multi-function PCI devices into a single device-group for the
+ * iommu_device_group interface.  This tells the iommu driver to pretend
+ * it cannot distinguish between functions of a device, exposing only one
+ * group for the device.  Useful for disallowing use of individual PCI
+ * functions from userspace drivers.
+ */
+int iommu_group_mf __read_mostly;
+
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
 /* Dummy device used for NULL arguments (normally ISA). */
@@ -168,6 +177,8 @@ static __init int iommu_setup(char *p)
 #endif
 		if (!strncmp(p, "pt", 2))
 			iommu_pass_through = 1;
+		if (!strncmp(p, "group_mf", 8))
+			iommu_group_mf = 1;
 
 		gart_parse_options(p);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 84a28ea45fa4..73c6a4268bf4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -44,6 +44,7 @@
 #include <linux/perf_event.h>
 #include <linux/uaccess.h>
 #include <linux/hash.h>
+#include <linux/pci.h>
 #include <trace/events/kvm.h>
 
 #define CREATE_TRACE_POINTS
@@ -2095,7 +2096,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = 0;
 		break;
 	case KVM_CAP_IOMMU:
-		r = iommu_found();
+		r = iommu_present(&pci_bus_type);
 		break;
 	case KVM_CAP_MCE:
 		r = KVM_MAX_MCE_BANKS;