[PART2 RFC v1 1/9] iommu/amd: Detect and enable guest vAPIC support

[Suravee Suthikulpanit]

From: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>

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 mode (w/ 32-bit IRTE)
    * ga    : Guest vAPIC interrupt remapping mode (w/ 128-bit IRTE)

Note that the GA mode also supports legacy interrupt remapping
for non-passthrough devices with the 128-bit IRTE.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
---
 drivers/iommu/amd_iommu_init.c  | 74 +++++++++++++++++++++++++++++++++++++----
 drivers/iommu/amd_iommu_proto.h |  1 +
 drivers/iommu/amd_iommu_types.h | 14 ++++++++
 3 files changed, 83 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index bf4959f..83a5300 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -131,6 +131,7 @@ struct ivmd_header {
 bool amd_iommu_dump;
 bool amd_iommu_irq_remap __read_mostly;
 
+int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_GA;
 static bool amd_iommu_detected;
 static bool __initdata amd_iommu_disabled;
 
@@ -1087,6 +1088,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 		iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
 	}
 
+	if (((h->efr & (0x1 << 6)) == 0))
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+
 	iommu->mmio_base = iommu_map_mmio_space(iommu->mmio_phys,
 						iommu->mmio_phys_end);
 	if (!iommu->mmio_base)
@@ -1283,6 +1287,14 @@ 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 >= AMD_IOMMU_GUEST_IR_GA &&
+	    !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;
 
@@ -1340,16 +1352,23 @@ 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)
 		pr_info("AMD-Vi: Interrupt remapping enabled\n");
+	if (amd_iommu_guest_ir)
+		pr_info("AMD-Vi: AVIC enabled (%#x)\n", amd_iommu_guest_ir);
 }
 
 static int __init amd_iommu_init_pci(void)
@@ -1647,6 +1666,20 @@ static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
 			       iommu->stored_addr_lo | 1);
 }
 
+static void iommu_enable_ga(struct amd_iommu *iommu)
+{
+	switch (amd_iommu_guest_ir) {
+	case AMD_IOMMU_GUEST_IR_GA:
+		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;
+	}
+}
+
 /*
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
@@ -1662,9 +1695,13 @@ 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);
 	}
+
+	if (amd_iommu_guest_ir >= AMD_IOMMU_GUEST_IR_GA)
+		amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP);
 }
 
 static void enable_iommus_v2(void)
@@ -1690,6 +1727,9 @@ static void disable_iommus(void)
 
 	for_each_iommu(iommu)
 		iommu_disable(iommu);
+
+	if (amd_iommu_guest_ir >= AMD_IOMMU_GUEST_IR_GA)
+		amd_iommu_irq_ops.capability &= ~(1 << IRQ_POSTING_CAP);
 }
 
 /*
@@ -1929,10 +1969,16 @@ static int __init early_amd_iommu_init(void)
 		 * remapping tables.
 		 */
 		ret = -ENOMEM;
-		amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
-				MAX_IRQS_PER_TABLE * sizeof(u32),
-				IRQ_TABLE_ALIGNMENT,
-				0, NULL);
+		if (amd_iommu_guest_ir == AMD_IOMMU_GUEST_IR_LEGACY)
+			amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
+					MAX_IRQS_PER_TABLE * sizeof(u32),
+					IRQ_TABLE_ALIGNMENT,
+					0, NULL);
+		else
+			amd_iommu_irq_cache = kmem_cache_create("irq_remap_cache",
+					MAX_IRQS_PER_TABLE * (sizeof(u64) * 2),
+					IRQ_TABLE_ALIGNMENT,
+					0, NULL);
 		if (!amd_iommu_irq_cache)
 			goto out;
 
@@ -2128,7 +2174,7 @@ static int __init amd_iommu_init(void)
 	ret = iommu_go_to_state(IOMMU_INITIALIZED);
 	if (ret) {
 		free_dma_resources();
-		if (!irq_remapping_enabled) {
+		if (!irq_remapping_enabled && !amd_iommu_guest_ir) {
 			disable_iommus();
 			free_on_init_error();
 		} else {
@@ -2185,6 +2231,21 @@ 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, "ga", 2) == 0) {
+			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_GA;
+			break;
+		}
+	}
+	return 1;
+}
+
 static int __init parse_amd_iommu_options(char *str)
 {
 	for (; *str; ++str) {
@@ -2261,6 +2322,7 @@ static int __init parse_ivrs_hpet(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);
 
diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h
index 0bd9eb3..faa3b48 100644
--- a/drivers/iommu/amd_iommu_proto.h
+++ b/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;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 9d32b20..95414120 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/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
@@ -694,4 +697,15 @@ struct __iommu_counter {
 
 #endif /* CONFIG_AMD_IOMMU_STATS */
 
+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 GA and fallback to only support
+	 * legacy interrupt remapping via 128-bit IRTE.
+	 */
+	AMD_IOMMU_GUEST_IR_LEGACY_GA,
+	AMD_IOMMU_GUEST_IR_GA,
+};
+
 #endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
-- 
1.9.1