[PATCH v2] hw/i386/pc: Avoid overlap between CXL window and PCI 64bit BARs in QEMU

[PATCH v2] hw/i386/pc: Avoid overlap between CXL window and PCI 64bit BARs in QEMU

[peng guo via]

When using a CXL Type 3 device together with a virtio 9p device in QEMU on a 
physical server, the 9p device fails to initialize properly. The kernel reports
the following error:

    virtio: device uses modern interface but does not have VIRTIO_F_VERSION_1
    9pnet_virtio virtio0: probe with driver 9pnet_virtio failed with error -22
 
Further investigation revealed that the 64-bit BAR space assigned to the 9pnet
device was overlapped by the memory window allocated for the CXL devices. As a
result, the kernel could not correctly access the BAR region, causing the
virtio device to malfunction.
 
An excerpt from /proc/iomem shows:
 
    480010000-cffffffff : CXL Window 0
      480010000-4bfffffff : PCI Bus 0000:00
      4c0000000-4c01fffff : PCI Bus 0000:0c
        4c0000000-4c01fffff : PCI Bus 0000:0d
      4c0200000-cffffffff : PCI Bus 0000:00
        4c0200000-4c0203fff : 0000:00:03.0
          4c0200000-4c0203fff : virtio-pci-modern

To address this issue, this patch adds the reserved memory end calculation 
for cxl devices to reserve sufficient address space and ensure that CXL memory 
windows are allocated beyond all PCI 64-bit BARs. This prevents overlap with 
64-bit BARs regions such as those used by virtio or other pcie devices, 
resolving the conflict.

QEMU Build Configuration:

    ./configure --prefix=/home/work/qemu_master/build/ \
                --target-list=x86_64-softmmu \
                --enable-kvm \
                --enable-virtfs

QEMU Boot Command:

    sudo /home/work/qemu_master/qemu/build/qemu-system-x86_64 \
        -nographic -machine q35,cxl=on -enable-kvm -m 16G -smp 8 \
        -hda /home/work/gp_qemu/rootfs.img \
        -virtfs local,path=/home/work/gp_qemu/share,mount_tag=host0,security_model=passthrough,id=host0 \
        -kernel /home/work/linux_output/arch/x86/boot/bzImage \
        --append "console=ttyS0 crashkernel=256M root=/dev/sda rootfstype=ext4 rw loglevel=8" \
        -object memory-backend-ram,id=vmem0,share=on,size=4096M \
        -device pxb-cxl,bus_nr=12,bus=pcie.0,id=cxl.1 \
        -device cxl-rp,port=0,bus=cxl.1,id=root_port13,chassis=0,slot=2 \
        -device cxl-type3,bus=root_port13,volatile-memdev=vmem0,id=cxl-vmem0,sn=0x123456789 \
        -M cxl-fmw.0.targets.0=cxl.1,cxl-fmw.0.size=4G

Fixes: 03b39fcf64bc ("hw/cxl: Make the CXL fixed memory window setup a machine parameter")
Signed-off-by: peng guo <engguopeng@buaa.edu.cn>
---
 v1 -> v2: Make the patch clearer and add fixes

 hw/i386/pc.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 2f58e73d3347..0f10f6edd23e 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -975,16 +975,16 @@ void pc_memory_init(PCMachineState *pcms,
 
     rom_set_fw(fw_cfg);
 
-    if (machine->device_memory) {
-        uint64_t *val = g_malloc(sizeof(*val));
-        uint64_t res_mem_end;
+    uint64_t res_mem_end = 0;
+    if (pcms->cxl_devices_state.is_enabled) {
+        res_mem_end = cxl_resv_end;
+    } else if (machine->device_memory) {
+        res_mem_end = machine->device_memory->base
+                        + memory_region_size(&machine->device_memory->mr);
+    }
 
-        if (pcms->cxl_devices_state.is_enabled) {
-            res_mem_end = cxl_resv_end;
-        } else {
-            res_mem_end = machine->device_memory->base
-                          + memory_region_size(&machine->device_memory->mr);
-        }
+    if (res_mem_end) {
+        uint64_t *val = g_malloc(sizeof(*val));
         *val = cpu_to_le64(ROUND_UP(res_mem_end, 1 * GiB));
         fw_cfg_add_file(fw_cfg, "etc/reserved-memory-end", val, sizeof(*val));
     }
-- 
2.43.0

Re: [PATCH v2] hw/i386/pc: Avoid overlap between CXL window and PCI 64bit BARs in QEMU

[Jonathan Cameron via]

On Mon,  4 Aug 2025 22:24:21 +0800
peng guo <engguopeng@buaa.edu.cn> wrote:

> When using a CXL Type 3 device together with a virtio 9p device in QEMU on a 
> physical server, the 9p device fails to initialize properly. The kernel reports
> the following error:
> 
>     virtio: device uses modern interface but does not have VIRTIO_F_VERSION_1
>     9pnet_virtio virtio0: probe with driver 9pnet_virtio failed with error -22
>  
> Further investigation revealed that the 64-bit BAR space assigned to the 9pnet
> device was overlapped by the memory window allocated for the CXL devices. As a
> result, the kernel could not correctly access the BAR region, causing the
> virtio device to malfunction.
>  
> An excerpt from /proc/iomem shows:
>  
>     480010000-cffffffff : CXL Window 0
>       480010000-4bfffffff : PCI Bus 0000:00
>       4c0000000-4c01fffff : PCI Bus 0000:0c
>         4c0000000-4c01fffff : PCI Bus 0000:0d
>       4c0200000-cffffffff : PCI Bus 0000:00
>         4c0200000-4c0203fff : 0000:00:03.0
>           4c0200000-4c0203fff : virtio-pci-modern
> 
> To address this issue, this patch adds the reserved memory end calculation 
> for cxl devices to reserve sufficient address space and ensure that CXL memory 
> windows are allocated beyond all PCI 64-bit BARs. This prevents overlap with 
> 64-bit BARs regions such as those used by virtio or other pcie devices, 
> resolving the conflict.
> 
> QEMU Build Configuration:
> 
>     ./configure --prefix=/home/work/qemu_master/build/ \
>                 --target-list=x86_64-softmmu \
>                 --enable-kvm \
>                 --enable-virtfs
> 
> QEMU Boot Command:
> 
>     sudo /home/work/qemu_master/qemu/build/qemu-system-x86_64 \
>         -nographic -machine q35,cxl=on -enable-kvm -m 16G -smp 8 \
>         -hda /home/work/gp_qemu/rootfs.img \
>         -virtfs local,path=/home/work/gp_qemu/share,mount_tag=host0,security_model=passthrough,id=host0 \
>         -kernel /home/work/linux_output/arch/x86/boot/bzImage \
>         --append "console=ttyS0 crashkernel=256M root=/dev/sda rootfstype=ext4 rw loglevel=8" \
>         -object memory-backend-ram,id=vmem0,share=on,size=4096M \
>         -device pxb-cxl,bus_nr=12,bus=pcie.0,id=cxl.1 \
>         -device cxl-rp,port=0,bus=cxl.1,id=root_port13,chassis=0,slot=2 \
>         -device cxl-type3,bus=root_port13,volatile-memdev=vmem0,id=cxl-vmem0,sn=0x123456789 \
>         -M cxl-fmw.0.targets.0=cxl.1,cxl-fmw.0.size=4G
> 
> Fixes: 03b39fcf64bc ("hw/cxl: Make the CXL fixed memory window setup a machine parameter")
> Signed-off-by: peng guo <engguopeng@buaa.edu.cn>
> ---
>  v1 -> v2: Make the patch clearer and add fixes
> 
>  hw/i386/pc.c | 18 +++++++++---------
>  1 file changed, 9 insertions(+), 9 deletions(-)
> 
> diff --git a/hw/i386/pc.c b/hw/i386/pc.c
> index 2f58e73d3347..0f10f6edd23e 100644
> --- a/hw/i386/pc.c
> +++ b/hw/i386/pc.c
> @@ -975,16 +975,16 @@ void pc_memory_init(PCMachineState *pcms,
>  
>      rom_set_fw(fw_cfg);
>  
> -    if (machine->device_memory) {
> -        uint64_t *val = g_malloc(sizeof(*val));
> -        uint64_t res_mem_end;
> +    uint64_t res_mem_end = 0;

Looking at local code style, it's declarations at top of scope not
inline.  That's what the coding style suggests as well:
https://qemu-project.gitlab.io/qemu/devel/style.html#declarations


Given we do want that 0 to be obviously set near here, you could go
with a final 
} else {
	res_mem_end = 0;
}

And not initialize at declaration (which will be up a long way).

> +    if (pcms->cxl_devices_state.is_enabled) {
> +        res_mem_end = cxl_resv_end;
> +    } else if (machine->device_memory) {
> +        res_mem_end = machine->device_memory->base
> +                        + memory_region_size(&machine->device_memory->mr);
> +    }
>  
> -        if (pcms->cxl_devices_state.is_enabled) {
> -            res_mem_end = cxl_resv_end;
> -        } else {
> -            res_mem_end = machine->device_memory->base
> -                          + memory_region_size(&machine->device_memory->mr);
> -        }
> +    if (res_mem_end) {
> +        uint64_t *val = g_malloc(sizeof(*val));
>          *val = cpu_to_le64(ROUND_UP(res_mem_end, 1 * GiB));
>          fw_cfg_add_file(fw_cfg, "etc/reserved-memory-end", val, sizeof(*val));
>      }