[PATCH] iommu/amd: Use cmpxchg_double() when updating 128-bit IRTE

[Suravee Suthikulpanit]

When using 128-bit interrupt-remapping table entry (IRTE) (a.k.a GA mode),
current driver disables interrupt remapping when it updates the IRTE
so that the upper and lower 64-bit values can be updated safely.

However, this creates a small window, where the interrupt could
arrive and result in IO_PAGE_FAULT (for interrupt) as shown below.

  IOMMU Driver            Device IRQ
  ============            ===========
  irte.RemapEn=0
       ...
   change IRTE            IRQ from device ==> IO_PAGE_FAULT !!
       ...
  irte.RemapEn=1

This scenario has been observed when changing irq affinity on a system
running I/O-intensive workload, in which the destination APIC ID
in the IRTE is updated.

Instead, use cmpxchg_double() to update the 128-bit IRTE at once without
disabling the interrupt remapping. However, this means several features,
which require GA (128-bit IRTE) support will also be affected if cmpxchg16b
is not supported (which is unprecedented for AMD processors w/ IOMMU).

Cc: stable@xxxxxxxxxxxxxxx
Fixes: 880ac60e2538 ("iommu/amd: Introduce interrupt remapping ops structure")
Reported-by: Sean Osborne <sean.m.osborne@xxxxxxxxxx>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
Tested-by: Erik Rockstrom <erik.rockstrom@xxxxxxxxxx>
Reviewed-by: Joao Martins <joao.m.martins@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20200903093822.52012-3-suravee.suthikulpanit@xxxxxxx
Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
---
Note: This patch is the back-port on top of the stable branch linux-5.4.y
for the upstream commit e52d58d54a32 ("iommu/amd: Use cmpxchg_double() when
updating 128-bit IRTE") since the original patch does not apply cleanly.

 drivers/iommu/Kconfig          |  2 +-
 drivers/iommu/amd_iommu.c      | 17 +++++++++++++----
 drivers/iommu/amd_iommu_init.c | 21 +++++++++++++++++++--
 3 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 390568afee9f..fc0160e8ed33 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -138,7 +138,7 @@ 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 fa91d856a43e..7b724f7b27a9 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3873,6 +3873,7 @@ 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;
@@ -3890,10 +3891,18 @@ 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;
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 135ae5222cf3..31d7e2d4f304 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1522,7 +1522,14 @@ 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;
 		break;
 	case 0x11:
@@ -1531,8 +1538,18 @@ 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;
+			break;
+		}
+
 		/*
 		 * Note: Since iommu_update_intcapxt() leverages
 		 * the IOMMU MMIO access to MSI capability block registers
-- 
2.17.1