Fix guest OS hang when 64bit PCI bar present

This patch addresses the issue fully described here:
http://lists.nongnu.org/archive/html/qemu-devel/2013-02/msg01804.html

Linux kernels prior to 2.6.36 do not disable the PCI device during
enumeration process. Since lower and higher parts of a 64bit BAR
are programmed separately this leads to qemu receiving a request to occupy
a completely wrong address region for a short period of time.
We have found that the boot process screws up completely if kvm-apic range
is overlapped even for a short period of time (it is fine for other
regions though).

This patch raises the priority of the kvm-apic memory region, so it is
never pushed out by PCI devices. The patch is quite safe as it does not
touch memory manager.

Signed-off-by: Alexey Korolev <akorolex@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

diff --git a/hw/sysbus.c b/hw/sysbus.c
index 6d9d1df41927b3390b872801ee006af20430fbb8..50c72327997654de494145d3b28a59fe6d4690e1 100644 (file)
--- a/hw/sysbus.c
+++ b/hw/sysbus.c
@@ -48,7 +48,8 @@ void sysbus_connect_irq(SysBusDevice *dev, int n, qemu_irq irq)
     }
 }
 
-void sysbus_mmio_map(SysBusDevice *dev, int n, hwaddr addr)
+static void sysbus_mmio_map_common(SysBusDevice *dev, int n, hwaddr addr,
+                                   bool may_overlap, unsigned priority)
 {
     assert(n >= 0 && n < dev->num_mmio);
 
@@ -61,11 +62,29 @@ void sysbus_mmio_map(SysBusDevice *dev, int n, hwaddr addr)
         memory_region_del_subregion(get_system_memory(), dev->mmio[n].memory);
     }
     dev->mmio[n].addr = addr;
-    memory_region_add_subregion(get_system_memory(),
-                                addr,
-                                dev->mmio[n].memory);
+    if (may_overlap) {
+        memory_region_add_subregion_overlap(get_system_memory(),
+                                            addr,
+                                            dev->mmio[n].memory,
+                                            priority);
+    }
+    else {
+        memory_region_add_subregion(get_system_memory(),
+                                    addr,
+                                    dev->mmio[n].memory);
+    }
 }
 
+void sysbus_mmio_map(SysBusDevice *dev, int n, hwaddr addr)
+{
+    sysbus_mmio_map_common(dev, n, addr, false, 0);
+}
+
+void sysbus_mmio_map_overlap(SysBusDevice *dev, int n, hwaddr addr,
+                             unsigned priority)
+{
+    sysbus_mmio_map_common(dev, n, addr, true, priority);
+}
 
 /* Request an IRQ source.  The actual IRQ object may be populated later.  */
 void sysbus_init_irq(SysBusDevice *dev, qemu_irq *p)

diff --git a/hw/sysbus.h b/hw/sysbus.h
index a7fcded6e7679520dd8017bf4d26ca9dc74586de..2100bd7d0781087903027484b83636d7b9cd23ec 100644 (file)
--- a/hw/sysbus.h
+++ b/hw/sysbus.h
@@ -56,6 +56,8 @@ void sysbus_init_ioports(SysBusDevice *dev, pio_addr_t ioport, pio_addr_t size);
 
 void sysbus_connect_irq(SysBusDevice *dev, int n, qemu_irq irq);
 void sysbus_mmio_map(SysBusDevice *dev, int n, hwaddr addr);
+void sysbus_mmio_map_overlap(SysBusDevice *dev, int n, hwaddr addr,
+                             unsigned priority);
 void sysbus_add_memory(SysBusDevice *dev, hwaddr addr,
                        MemoryRegion *mem);
 void sysbus_add_memory_overlap(SysBusDevice *dev, hwaddr addr,

diff --git a/target-i386/cpu.c b/target-i386/cpu.c
index 5582e5f4e6224c358883ba00aee8dc69f8235511..8fb736a5b4943af44112efd1525240d4be873c78 100644 (file)
--- a/target-i386/cpu.c
+++ b/target-i386/cpu.c
@@ -2088,7 +2088,8 @@ static void x86_cpu_apic_init(X86CPU *cpu, Error **errp)
         /* NOTE: the APIC is directly connected to the CPU - it is not
            on the global memory bus. */
         /* XXX: what if the base changes? */
-        sysbus_mmio_map(SYS_BUS_DEVICE(env->apic_state), 0, MSI_ADDR_BASE);
+        sysbus_mmio_map_overlap(SYS_BUS_DEVICE(env->apic_state), 0,
+                                MSI_ADDR_BASE, 0x1000);
         apic_mapped = 1;
     }
 }