iommu/amd: Detect and enable guest vAPIC support

This patch introduces a new IOMMU driver parameter, amd_iommu_guest_ir,
which can be used to specify different interrupt remapping mode for
passthrough devices to VM guest:
    * legacy: Legacy interrupt remapping (w/ 32-bit IRTE)
    * vapic : Guest vAPIC interrupt remapping (w/ GA mode 128-bit IRTE)

Note that in vapic mode, it can also supports legacy interrupt remapping
for non-passthrough devices with the 128-bit IRTE.

Signed-off-by: Suravee Suthikulpanit <[email protected]>
Signed-off-by: Joerg Roedel <[email protected]>

Author: ssuthiku-amd

Documentation/kernel-parameters.txt

@@ -460,6 +460,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			driver will print ACPI tables for AMD IOMMU during
 			IOMMU initialization.
 
+	amd_iommu_intr=	[HW,X86-64]
+			Specifies one of the following AMD IOMMU interrupt
+			remapping modes:
+			legacy     - Use legacy interrupt remapping mode.
+			vapic      - Use virtual APIC mode, which allows IOMMU
+			             to inject interrupts directly into guest.
+			             This mode requires kvm-amd.avic=1.
+			             (Default when IOMMU HW support is present.)
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>

drivers/iommu/amd_iommu_init.c

@@ -145,6 +145,8 @@ struct ivmd_header {
 bool amd_iommu_dump;
 bool amd_iommu_irq_remap __read_mostly;
 
+int amd_iommu_guest_ir;
+
 static bool amd_iommu_detected;
 static bool __initdata amd_iommu_disabled;
 static int amd_iommu_target_ivhd_type;
@@ -1258,13 +1260,17 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
+		if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		break;
 	case 0x11:
 	case 0x40:
 		if (h->efr_reg & (1 << 9))
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
+		if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		break;
 	default:
 		return -EINVAL;
@@ -1488,6 +1494,14 @@ static int iommu_init_pci(struct amd_iommu *iommu)
 	if (iommu_feature(iommu, FEATURE_PPR) && alloc_ppr_log(iommu))
 		return -ENOMEM;
 
+	/* Note: We have already checked GASup from IVRS table.
+	 *       Now, we need to make sure that GAMSup is set.
+	 */
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+	    !iommu_feature(iommu, FEATURE_GAM_VAPIC))
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+
+
 	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE))
 		amd_iommu_np_cache = true;
 
@@ -1545,16 +1559,24 @@ static void print_iommu_info(void)
 			dev_name(&iommu->dev->dev), iommu->cap_ptr);
 
 		if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
-			pr_info("AMD-Vi:  Extended features: ");
+			pr_info("AMD-Vi: Extended features (%#llx):\n",
+				iommu->features);
 			for (i = 0; i < ARRAY_SIZE(feat_str); ++i) {
 				if (iommu_feature(iommu, (1ULL << i)))
 					pr_cont(" %s", feat_str[i]);
 			}
+
+			if (iommu->features & FEATURE_GAM_VAPIC)
+				pr_cont(" GA_vAPIC");
+
 			pr_cont("\n");
 		}
 	}
-	if (irq_remapping_enabled)
+	if (irq_remapping_enabled) {
 		pr_info("AMD-Vi: Interrupt remapping enabled\n");
+		if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
+			pr_info("AMD-Vi: virtual APIC enabled\n");
+	}
 }
 
 static int __init amd_iommu_init_pci(void)
@@ -1862,6 +1884,22 @@ static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
 			       iommu->stored_addr_lo | 1);
 }
 
+static void iommu_enable_ga(struct amd_iommu *iommu)
+{
+#ifdef CONFIG_IRQ_REMAP
+	switch (amd_iommu_guest_ir) {
+	case AMD_IOMMU_GUEST_IR_VAPIC:
+		iommu_feature_enable(iommu, CONTROL_GAM_EN);
+		/* Fall through */
+	case AMD_IOMMU_GUEST_IR_LEGACY_GA:
+		iommu_feature_enable(iommu, CONTROL_GA_EN);
+		break;
+	default:
+		break;
+	}
+#endif
+}
+
 /*
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
@@ -1877,6 +1915,7 @@ static void early_enable_iommus(void)
 		iommu_enable_command_buffer(iommu);
 		iommu_enable_event_buffer(iommu);
 		iommu_set_exclusion_range(iommu);
+		iommu_enable_ga(iommu);
 		iommu_enable(iommu);
 		iommu_flush_all_caches(iommu);
 	}
@@ -2059,7 +2098,7 @@ static int __init early_amd_iommu_init(void)
 	struct acpi_table_header *ivrs_base;
 	acpi_size ivrs_size;
 	acpi_status status;
-	int i, ret = 0;
+	int i, remap_cache_sz, ret = 0;
 
 	if (!amd_iommu_detected)
 		return -ENODEV;
@@ -2157,10 +2196,14 @@ static int __init early_amd_iommu_init(void)
 		 * remapping tables.
 		 */
 		ret = -ENOMEM;
+		if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+			remap_cache_sz = MAX_IRQS_PER_TABLE * sizeof(u32);
+		else
+			remap_cache_sz = MAX_IRQS_PER_TABLE * (sizeof(u64) * 2);
 		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
-				MAX_IRQS_PER_TABLE * sizeof(u32),
-				IRQ_TABLE_ALIGNMENT,
-				0, NULL);
+							remap_cache_sz,
+							IRQ_TABLE_ALIGNMENT,
+							0, NULL);
 		if (!amd_iommu_irq_cache)
 			goto out;
 
@@ -2413,6 +2456,21 @@ static int __init parse_amd_iommu_dump(char *str)
 	return 1;
 }
 
+static int __init parse_amd_iommu_intr(char *str)
+{
+	for (; *str; ++str) {
+		if (strncmp(str, "legacy", 6) == 0) {
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			break;
+		}
+		if (strncmp(str, "vapic", 5) == 0) {
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
+			break;
+		}
+	}
+	return 1;
+}
+
 static int __init parse_amd_iommu_options(char *str)
 {
 	for (; *str; ++str) {
@@ -2521,6 +2579,7 @@ static int __init parse_ivrs_acpihid(char *str)
 
 __setup("amd_iommu_dump",	parse_amd_iommu_dump);
 __setup("amd_iommu=",		parse_amd_iommu_options);
+__setup("amd_iommu_intr=",	parse_amd_iommu_intr);
 __setup("ivrs_ioapic",		parse_ivrs_ioapic);
 __setup("ivrs_hpet",		parse_ivrs_hpet);
 __setup("ivrs_acpihid",		parse_ivrs_acpihid);

drivers/iommu/amd_iommu_proto.h

@@ -38,6 +38,7 @@ extern int amd_iommu_enable(void);
 extern void amd_iommu_disable(void);
 extern int amd_iommu_reenable(int);
 extern int amd_iommu_enable_faulting(void);
+extern int amd_iommu_guest_ir;
 
 /* IOMMUv2 specific functions */
 struct iommu_domain;

drivers/iommu/amd_iommu_types.h

@@ -92,6 +92,7 @@
 #define FEATURE_GA		(1ULL<<7)
 #define FEATURE_HE		(1ULL<<8)
 #define FEATURE_PC		(1ULL<<9)
+#define FEATURE_GAM_VAPIC	(1ULL<<21)
 
 #define FEATURE_PASID_SHIFT	32
 #define FEATURE_PASID_MASK	(0x1fULL << FEATURE_PASID_SHIFT)
@@ -146,6 +147,8 @@
 #define CONTROL_PPFINT_EN       0x0eULL
 #define CONTROL_PPR_EN          0x0fULL
 #define CONTROL_GT_EN           0x10ULL
+#define CONTROL_GA_EN           0x11ULL
+#define CONTROL_GAM_EN          0x19ULL
 
 #define CTRL_INV_TO_MASK	(7 << CONTROL_INV_TIMEOUT)
 #define CTRL_INV_TO_NONE	0
@@ -329,6 +332,12 @@
 #define IOMMU_CAP_NPCACHE 26
 #define IOMMU_CAP_EFR     27
 
+/* IOMMU Feature Reporting Field (for IVHD type 10h */
+#define IOMMU_FEAT_GASUP_SHIFT	6
+
+/* IOMMU Extended Feature Register (EFR) */
+#define IOMMU_EFR_GASUP_SHIFT	7
+
 #define MAX_DOMAIN_ID 65536
 
 /* Protection domain flags */
@@ -681,4 +690,19 @@ static inline int get_hpet_devid(int id)
 	return -EINVAL;
 }
 
+enum amd_iommu_intr_mode_type {
+	AMD_IOMMU_GUEST_IR_LEGACY,
+
+	/* This mode is not visible to users. It is used when
+	 * we cannot fully enable vAPIC and fallback to only support
+	 * legacy interrupt remapping via 128-bit IRTE.
+	 */
+	AMD_IOMMU_GUEST_IR_LEGACY_GA,
+	AMD_IOMMU_GUEST_IR_VAPIC,
+};
+
+#define AMD_IOMMU_GUEST_IR_GA(x)	(x == AMD_IOMMU_GUEST_IR_VAPIC || \
+					 x == AMD_IOMMU_GUEST_IR_LEGACY_GA)
+
+#define AMD_IOMMU_GUEST_IR_VAPIC(x)	(x == AMD_IOMMU_GUEST_IR_VAPIC)
 #endif /* _ASM_X86_AMD_IOMMU_TYPES_H */