diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index a608ac136a973b4081b7d4fe063a275531e0b42f..53dd814adeb57f94400b165f60d925188db887f2 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -161,7 +161,7 @@ config AMD_IOMMU
 	select PCI_PASID
 	select IOMMU_API
 	select IOMMU_IOVA
-	depends on X86_64 && PCI && ACPI
+	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
 	---help---
 	  With this option you can enable support for AMD IOMMU hardware in
 	  your system. An IOMMU is a hardware component which provides
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index a1f417694a48d8b3925e67857d12ffe1add4edb2..9db6a8af9617e813a0858b9dd974007b489f3e96 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3807,6 +3807,7 @@ static int alloc_irq_index(u16 devid, int count, bool align)
 static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 			  struct amd_ir_data *data)
 {
+	bool ret;
 	struct irq_remap_table *table;
 	struct amd_iommu *iommu;
 	unsigned long flags;
@@ -3824,10 +3825,18 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
-	entry->lo.fields_remap.valid = 0;
-	entry->hi.val = irte->hi.val;
-	entry->lo.val = irte->lo.val;
-	entry->lo.fields_remap.valid = 1;
+
+	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+			entry->lo.val, entry->hi.val,
+			irte->lo.val, irte->hi.val);
+	/*
+	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+	 * and it cannot be updated by the hardware or other processors
+	 * behind us, so the return value of cmpxchg16 should be the
+	 * same as the old value.
+	 */
+	WARN_ON(!ret);
+
 	if (data)
 		data->ref = entry;
 
@@ -4379,10 +4388,12 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	} else {
 		/* Un-Setting */
 		struct irq_cfg *cfg = irqd_cfg(data);
+		u64 valid = irte->lo.fields_remap.valid;
 
 		irte->hi.val = 0;
 		irte->lo.val = 0;
 		irte->hi.fields.vector = cfg->vector;
+		irte->lo.fields_remap.valid = valid;
 		irte->lo.fields_remap.guest_mode = 0;
 		irte->lo.fields_remap.destination =
 				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 29bf91e50d4131f562990d6ce21c222cbc8f578a..abd327653d339bed467dc8670f40c882817dbd95 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1525,7 +1525,14 @@ 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))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling it.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+			((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		if (((h->efr_attr & (0x1 << IOMMU_FEAT_XTSUP_SHIFT)) == 0))
 			amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
@@ -1536,7 +1543,14 @@ 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_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * XT, GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling them.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+			((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		if (((h->efr_reg & (0x1 << IOMMU_EFR_XTSUP_SHIFT)) == 0))
 			amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 0b8ee173cf3a6a3d976d882ad3f02a3c8f80fd91..2f15b9de12c4671dd53977b85760775e501c70f2 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -83,7 +83,8 @@ static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
  * users set the same bit, one user will return remain bits, otherwise
  * return 0.
  */
-static int bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr)
+static unsigned long
+bitmap_set_ll(unsigned long *map, unsigned long start, unsigned long nr)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned long size = start + nr;