[Qemu-devel] [PATCH v2] x86: ioapic: conditionally upgrade IOAPIC version

[Peter Xu]

IOMMU IR and IOAPIC legacy devices (e.g., e1000) cannot work well
together with some old Linux kernels (upstream before v4.0, or any
released RHEL kernels). This patch fixes it.

The problem is that: some old linux kernels (with IR enabled) only
support IOAPIC chips with version 0x20. New kernels after commit d32932d
("x86/irq: Convert IOAPIC to use hierarchical irqdomain interfaces")
fixed this problem. To make sure we can work with even old kernels,
let's upgrade our IOAPIC to version 0x20.

To make sure we have minimum impact on old systems, IOAPIC version is
only boosted to 0x20 when vIOMMU IR is enabled. Besides that, the old
version 0x11 is used.

Signed-off-by: Peter Xu <address@hidden>
---
 hw/intc/ioapic.c                  | 25 ++++++++++++++++++++++++-
 include/hw/i386/ioapic_internal.h |  3 +--
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/hw/intc/ioapic.c b/hw/intc/ioapic.c
index 2d3282a..cd3f283 100644
--- a/hw/intc/ioapic.c
+++ b/hw/intc/ioapic.c
@@ -244,6 +244,23 @@ void ioapic_dump_state(Monitor *mon, const QDict *qdict)
     }
 }
 
+static uint32_t ioapic_get_version(void)
+{
+    X86IOMMUState *iommu = x86_iommu_get_default();
+
+    /*
+     * If we enabled vIOMMU IR, we provide a upgraded version of
+     * IOAPIC 0x20, which support explicit EOI request from guest.
+     * This fixes a bug that IR not working on some old upstream
+     * kernels (before v4.0, commit d32932d) or most RHEL ones.
+     */
+    if (iommu && iommu->intr_supported) {
+        return 0x20;
+    }
+
+    return 0x11;
+}
+
 static uint64_t
 ioapic_mem_read(void *opaque, hwaddr addr, unsigned int size)
 {
@@ -265,7 +282,7 @@ ioapic_mem_read(void *opaque, hwaddr addr, unsigned int 
size)
             val = s->id << IOAPIC_ID_SHIFT;
             break;
         case IOAPIC_REG_VER:
-            val = IOAPIC_VERSION |
+            val = ioapic_get_version() |
                 ((IOAPIC_NUM_PINS - 1) << IOAPIC_VER_ENTRIES_SHIFT);
             break;
         default:
@@ -354,6 +371,12 @@ ioapic_mem_write(void *opaque, hwaddr addr, uint64_t val,
             }
         }
         break;
+    case IOAPIC_EOI:
+        if (size != 4 || ioapic_get_version() != 0x20) {
+            break;
+        }
+        ioapic_eoi_broadcast(val);
+        break;
     }
 
     ioapic_update_kvm_routes(s);
diff --git a/include/hw/i386/ioapic_internal.h 
b/include/hw/i386/ioapic_internal.h
index d89ea1b..6f266c3 100644
--- a/include/hw/i386/ioapic_internal.h
+++ b/include/hw/i386/ioapic_internal.h
@@ -29,8 +29,6 @@
 
 #define MAX_IOAPICS                     1
 
-#define IOAPIC_VERSION                  0x11
-
 #define IOAPIC_LVT_DEST_SHIFT           56
 #define IOAPIC_LVT_DEST_IDX_SHIFT       48
 #define IOAPIC_LVT_MASKED_SHIFT         16
@@ -71,6 +69,7 @@
 
 #define IOAPIC_IOREGSEL                 0x00
 #define IOAPIC_IOWIN                    0x10
+#define IOAPIC_EOI                      0x40
 
 #define IOAPIC_REG_ID                   0x00
 #define IOAPIC_REG_VER                  0x01
-- 
2.4.11