There are two ways of creating virtual functions: by using the sriov-pf device
parameter (this way, creating a user created VF and binding it to a PF), or
by using a device specific parameter, where the device manually creates a given
amount of VFs.
When a PCI device is realized, the device specific realize function is called
first, and then the pcie_sriov_register_device function is called, which checks
whether the device that has been created is a user created VF, and if it is the
case and the device allows this kind of VFs, it inserts it into a hashmap, with
the key being the ID of the PF, and the items being arrays of VFs.
User created VFs are instantiated independently, and later, when the PF calls
pcie_sriov_pf_init_from_user_created_vfs, it discovers its VFs from the hashmap
mentioned previously, and sets up in their PCIDevice.ex.sriov_pf structure
the pointer to the PF. This means that, during realization, VFs have no access
to the PF.
Device created VFs are instantiated during or after PF realization using the
pcie_sriov_pf_init function, which sets up for the VFs the pointer to the PF
before their realization, so when they're realized, they can access the PF
with no issues.
The problem here is that pcie_sriov_register_device is called after the
realization, and not before. This means that when a user created VF is created
for a device which does not support user created VFs, but supports device
created VFs, the realize function will notice that a VF is being created, and
may try to access the PF, causing a null pointer dereference fault.
Fix this by placing the user created VF check and registering before the
realization. This way, incorrectly created user created VFs will be noticed,
and device creation will be aborted.
Additionally, remove from the pcie_sriov_register_device function the top
check. It seems that this check is done to error out if the PF failed for some
reason to initialize its list of user created VFs. However, in such situations,
the pcie_sriov_pf_init_from_user_created_vfs function will error during
realization, and it will be caught before the check is done at all. Moreover,
since now pcie_sriov_register_device is called before realization, the check
will always fail for PFs with user created VFs, because the list will be
populated during realization.
The rest of the function though, correctly errors out if a user created VF
is created for an unsupported device type, if a VF is created for a non-PCIe
device, or if the PF is already instantiated, with now the advantage being
that the check is done before the VF instantiation.
When instantiating a user created VF for a NVME controller:
Command line:
qemu-system-x86_64 -device nvme-subsys,id=subsys0 \
-device nvme,id=vctrl0,sriov-pf=ctrl0,subsys=subsys0 \
-device nvme,id=ctrl0,subsys=subsys0,serial=s
ASAN splat:
../hw/nvme/ctrl.c:9613:28: runtime error: member access within null pointer of type 'struct NvmeCtrl'
AddressSanitizer:DEADLYSIGNAL
=================================================================
==91050==ERROR: AddressSanitizer: SEGV on unknown address 0x000000001cf0 (pc 0x7f79a8573dcd bp 0x7ffd622c1bc0 sp 0x7ffd622c1b68 T0)
==91050==The signal is caused by a READ memory access.
#0 0x7f79a8573dcd (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
#1 0x5644c6c0266e in nvme_realize ../hw/nvme/ctrl.c:9613
#2 0x5644c6c67213 in pci_qdev_realize ../hw/pci/pci.c:2316
#3 0x5644c7a2cfc1 in device_set_realized ../hw/core/qdev.c:514
#4 0x5644c7a4f767 in property_set_bool ../qom/object.c:2484
#5 0x5644c7a48d0b in object_property_set ../qom/object.c:1548
#6 0x5644c7a568a5 in object_property_set_qobject ../qom/qom-qobject.c:28
#7 0x5644c7a49385 in object_property_set_bool ../qom/object.c:1618
#8 0x5644c7a2aeb0 in qdev_realize ../hw/core/qdev.c:277
#9 0x5644c735f29f in qdev_device_add_from_qdict ../system/qdev-monitor.c:740
#10 0x5644c735f3ab in qdev_device_add ../system/qdev-monitor.c:758
#11 0x5644c72b1901 in device_init_func ../system/vl.c:1217
#12 0x5644c829d4a3 in qemu_opts_foreach ../util/qemu-option.c:1148
#13 0x5644c72bc33e in qemu_create_cli_devices ../system/vl.c:2762
#14 0x5644c72bcaa1 in qmp_x_exit_preconfig ../system/vl.c:2822
#15 0x5644c72c3241 in qemu_init ../system/vl.c:3862
#16 0x5644c801abf8 in main ../system/main.c:71
#17 0x7f79a8427780 (/usr/lib/libc.so.6+0x27780) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
#18 0x7f79a84278b8 in __libc_start_main (/usr/lib/libc.so.6+0x278b8) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
#19 0x5644c5f0a1f4 in _start (BuildId: 8483f952216d9e345c3744300d0aefa38feb50d7)
==91050==Register values:
rax = 0x00007e49988640f0 rbx = 0x00007e49988640f0 rcx = 0x00000fc9b3104828 rdx = 0x0000000000000058
rdi = 0x00007e49988640f0 rsi = 0x0000000000001cf0 rbp = 0x00007ffd622c1bc0 rsp = 0x00007ffd622c1b68
r8 = 0x00000fc9b3104829 r9 = 0x00000fc9b3104828 r10 = 0x00000fc9b310481e r11 = 0x00000fc9b310481e
r12 = 0x0000000000001cf0 r13 = 0x00000f6f32e78578 r14 = 0x00000000ffffffff r15 = 0x00007ffd622c1c10
AddressSanitizer can not provide additional info.
SUMMARY: AddressSanitizer: SEGV (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
==91050==ABORTING
Cc: qemu-stable@nongnu.org
Fixes: 19e55471d4e8 ("pcie_sriov: Allow user to create SR-IOV device")
Signed-off-by: Daniel Paziyski <danielpaziyski@gmail.com>
---
hw/pci/pci.c | 11 ++++++-----
hw/pci/pcie_sriov.c | 6 ------
2 files changed, 6 insertions(+), 11 deletions(-)
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index d3191609e2..a5b4482bb6 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -2312,20 +2312,21 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
if (pci_dev == NULL)
return;
+ if (!pcie_sriov_register_device(pci_dev, errp)) {
+ do_pci_unregister_device(pci_dev);
+ return;
+ }
+
if (pc->realize) {
pc->realize(pci_dev, &local_err);
if (local_err) {
error_propagate(errp, local_err);
+ pcie_sriov_unregister_device(pci_dev);
do_pci_unregister_device(pci_dev);
return;
}
}
- if (!pcie_sriov_register_device(pci_dev, errp)) {
- pci_qdev_unrealize(DEVICE(pci_dev));
- return;
- }
-
/*
* A PCIe Downstream Port that do not have ARI Forwarding enabled must
* associate only Device 0 with the device attached to the bus
diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index c41ac95bee..69930c7b8c 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -357,12 +357,6 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
{
- if (!dev->exp.sriov_pf.vf && dev->qdev.id &&
- pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
- error_setg(errp, "attaching user-created SR-IOV VF unsupported");
- return false;
- }
-
if (dev->sriov_pf) {
PCIDevice *pci_pf;
GPtrArray *pf;
--
2.55.0On Wed, Aug 05, 2026 at 02:45:18PM +0200, Daniel Paziyski wrote:
> There are two ways of creating virtual functions: by using the sriov-pf device
> parameter (this way, creating a user created VF and binding it to a PF), or
> by using a device specific parameter, where the device manually creates a given
> amount of VFs.
>
> When a PCI device is realized, the device specific realize function is called
> first, and then the pcie_sriov_register_device function is called, which checks
> whether the device that has been created is a user created VF, and if it is the
> case and the device allows this kind of VFs, it inserts it into a hashmap, with
> the key being the ID of the PF, and the items being arrays of VFs.
>
> User created VFs are instantiated independently, and later, when the PF calls
> pcie_sriov_pf_init_from_user_created_vfs, it discovers its VFs from the hashmap
> mentioned previously, and sets up in their PCIDevice.ex.sriov_pf structure
> the pointer to the PF. This means that, during realization, VFs have no access
> to the PF.
>
> Device created VFs are instantiated during or after PF realization using the
> pcie_sriov_pf_init function, which sets up for the VFs the pointer to the PF
> before their realization, so when they're realized, they can access the PF
> with no issues.
>
> The problem here is that pcie_sriov_register_device is called after the
> realization, and not before. This means that when a user created VF is created
> for a device which does not support user created VFs, but supports device
> created VFs, the realize function will notice that a VF is being created, and
> may try to access the PF, causing a null pointer dereference fault.
>
> Fix this by placing the user created VF check and registering before the
> realization. This way, incorrectly created user created VFs will be noticed,
> and device creation will be aborted.
>
> Additionally, remove from the pcie_sriov_register_device function the top
> check. It seems that this check is done to error out if the PF failed for some
> reason to initialize its list of user created VFs. However, in such situations,
> the pcie_sriov_pf_init_from_user_created_vfs function will error during
> realization, and it will be caught before the check is done at all. Moreover,
> since now pcie_sriov_register_device is called before realization, the check
> will always fail for PFs with user created VFs, because the list will be
> populated during realization.
>
> The rest of the function though, correctly errors out if a user created VF
> is created for an unsupported device type, if a VF is created for a non-PCIe
> device, or if the PF is already instantiated, with now the advantage being
> that the check is done before the VF instantiation.
>
> When instantiating a user created VF for a NVME controller:
>
> Command line:
>
> qemu-system-x86_64 -device nvme-subsys,id=subsys0 \
> -device nvme,id=vctrl0,sriov-pf=ctrl0,subsys=subsys0 \
> -device nvme,id=ctrl0,subsys=subsys0,serial=s
>
> ASAN splat:
>
> ../hw/nvme/ctrl.c:9613:28: runtime error: member access within null pointer of type 'struct NvmeCtrl'
> AddressSanitizer:DEADLYSIGNAL
> =================================================================
> ==91050==ERROR: AddressSanitizer: SEGV on unknown address 0x000000001cf0 (pc 0x7f79a8573dcd bp 0x7ffd622c1bc0 sp 0x7ffd622c1b68 T0)
> ==91050==The signal is caused by a READ memory access.
> #0 0x7f79a8573dcd (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> #1 0x5644c6c0266e in nvme_realize ../hw/nvme/ctrl.c:9613
> #2 0x5644c6c67213 in pci_qdev_realize ../hw/pci/pci.c:2316
> #3 0x5644c7a2cfc1 in device_set_realized ../hw/core/qdev.c:514
> #4 0x5644c7a4f767 in property_set_bool ../qom/object.c:2484
> #5 0x5644c7a48d0b in object_property_set ../qom/object.c:1548
> #6 0x5644c7a568a5 in object_property_set_qobject ../qom/qom-qobject.c:28
> #7 0x5644c7a49385 in object_property_set_bool ../qom/object.c:1618
> #8 0x5644c7a2aeb0 in qdev_realize ../hw/core/qdev.c:277
> #9 0x5644c735f29f in qdev_device_add_from_qdict ../system/qdev-monitor.c:740
> #10 0x5644c735f3ab in qdev_device_add ../system/qdev-monitor.c:758
> #11 0x5644c72b1901 in device_init_func ../system/vl.c:1217
> #12 0x5644c829d4a3 in qemu_opts_foreach ../util/qemu-option.c:1148
> #13 0x5644c72bc33e in qemu_create_cli_devices ../system/vl.c:2762
> #14 0x5644c72bcaa1 in qmp_x_exit_preconfig ../system/vl.c:2822
> #15 0x5644c72c3241 in qemu_init ../system/vl.c:3862
> #16 0x5644c801abf8 in main ../system/main.c:71
> #17 0x7f79a8427780 (/usr/lib/libc.so.6+0x27780) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> #18 0x7f79a84278b8 in __libc_start_main (/usr/lib/libc.so.6+0x278b8) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> #19 0x5644c5f0a1f4 in _start (BuildId: 8483f952216d9e345c3744300d0aefa38feb50d7)
>
> ==91050==Register values:
> rax = 0x00007e49988640f0 rbx = 0x00007e49988640f0 rcx = 0x00000fc9b3104828 rdx = 0x0000000000000058
> rdi = 0x00007e49988640f0 rsi = 0x0000000000001cf0 rbp = 0x00007ffd622c1bc0 rsp = 0x00007ffd622c1b68
> r8 = 0x00000fc9b3104829 r9 = 0x00000fc9b3104828 r10 = 0x00000fc9b310481e r11 = 0x00000fc9b310481e
> r12 = 0x0000000000001cf0 r13 = 0x00000f6f32e78578 r14 = 0x00000000ffffffff r15 = 0x00007ffd622c1c10
> AddressSanitizer can not provide additional info.
> SUMMARY: AddressSanitizer: SEGV (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> ==91050==ABORTING
>
> Cc: qemu-stable@nongnu.org
> Fixes: 19e55471d4e8 ("pcie_sriov: Allow user to create SR-IOV device")
> Signed-off-by: Daniel Paziyski <danielpaziyski@gmail.com>
> ---
> hw/pci/pci.c | 11 ++++++-----
> hw/pci/pcie_sriov.c | 6 ------
> 2 files changed, 6 insertions(+), 11 deletions(-)
>
> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
> index d3191609e2..a5b4482bb6 100644
> --- a/hw/pci/pci.c
> +++ b/hw/pci/pci.c
> @@ -2312,20 +2312,21 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
> if (pci_dev == NULL)
> return;
>
> + if (!pcie_sriov_register_device(pci_dev, errp)) {
> + do_pci_unregister_device(pci_dev);
This skips acpi-index rollback which pci_qdev_unrealize currently does.
Needs generic PCI cleanup.
> + return;
> + }
> +
> if (pc->realize) {
> pc->realize(pci_dev, &local_err);
> if (local_err) {
> error_propagate(errp, local_err);
> + pcie_sriov_unregister_device(pci_dev);
> do_pci_unregister_device(pci_dev);
> return;
> }
> }
>
> - if (!pcie_sriov_register_device(pci_dev, errp)) {
> - pci_qdev_unrealize(DEVICE(pci_dev));
> - return;
> - }
> -
> /*
> * A PCIe Downstream Port that do not have ARI Forwarding enabled must
> * associate only Device 0 with the device attached to the bus
> diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
> index c41ac95bee..69930c7b8c 100644
> --- a/hw/pci/pcie_sriov.c
> +++ b/hw/pci/pcie_sriov.c
> @@ -357,12 +357,6 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
>
> bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
> {
> - if (!dev->exp.sriov_pf.vf && dev->qdev.id &&
> - pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
> - error_setg(errp, "attaching user-created SR-IOV VF unsupported");
> - return false;
> - }
> -
> if (dev->sriov_pf) {
> PCIDevice *pci_pf;
> GPtrArray *pf;
> --
> 2.55.0
On Tue, 1 Sept 2026 at 13:19, Michael S. Tsirkin <mst@redhat.com> wrote:
>
> On Wed, Aug 05, 2026 at 02:45:18PM +0200, Daniel Paziyski wrote:
>> There are two ways of creating virtual functions: by using the sriov-pf device
>> parameter (this way, creating a user created VF and binding it to a PF), or
>> by using a device specific parameter, where the device manually creates a given
>> amount of VFs.
>>
>> When a PCI device is realized, the device specific realize function is called
>> first, and then the pcie_sriov_register_device function is called, which checks
>> whether the device that has been created is a user created VF, and if it is the
>> case and the device allows this kind of VFs, it inserts it into a hashmap, with
>> the key being the ID of the PF, and the items being arrays of VFs.
>>
>> User created VFs are instantiated independently, and later, when the PF calls
>> pcie_sriov_pf_init_from_user_created_vfs, it discovers its VFs from the hashmap
>> mentioned previously, and sets up in their PCIDevice.ex.sriov_pf structure
>> the pointer to the PF. This means that, during realization, VFs have no access
>> to the PF.
>>
>> Device created VFs are instantiated during or after PF realization using the
>> pcie_sriov_pf_init function, which sets up for the VFs the pointer to the PF
>> before their realization, so when they're realized, they can access the PF
>> with no issues.
>>
>> The problem here is that pcie_sriov_register_device is called after the
>> realization, and not before. This means that when a user created VF is created
>> for a device which does not support user created VFs, but supports device
>> created VFs, the realize function will notice that a VF is being created, and
>> may try to access the PF, causing a null pointer dereference fault.
>>
>> Fix this by placing the user created VF check and registering before the
>> realization. This way, incorrectly created user created VFs will be noticed,
>> and device creation will be aborted.
>>
>> Additionally, remove from the pcie_sriov_register_device function the top
>> check. It seems that this check is done to error out if the PF failed for some
>> reason to initialize its list of user created VFs. However, in such situations,
>> the pcie_sriov_pf_init_from_user_created_vfs function will error during
>> realization, and it will be caught before the check is done at all. Moreover,
>> since now pcie_sriov_register_device is called before realization, the check
>> will always fail for PFs with user created VFs, because the list will be
>> populated during realization.
>>
>> The rest of the function though, correctly errors out if a user created VF
>> is created for an unsupported device type, if a VF is created for a non-PCIe
>> device, or if the PF is already instantiated, with now the advantage being
>> that the check is done before the VF instantiation.
>>
>> When instantiating a user created VF for a NVME controller:
>>
>> Command line:
>>
>> qemu-system-x86_64 -device nvme-subsys,id=subsys0 \
>> -device nvme,id=vctrl0,sriov-pf=ctrl0,subsys=subsys0 \
>> -device nvme,id=ctrl0,subsys=subsys0,serial=s
>>
>> ASAN splat:
>>
>> ../hw/nvme/ctrl.c:9613:28: runtime error: member access within null pointer of type 'struct NvmeCtrl'
>> AddressSanitizer:DEADLYSIGNAL
>> =================================================================
>> ==91050==ERROR: AddressSanitizer: SEGV on unknown address 0x000000001cf0 (pc 0x7f79a8573dcd bp 0x7ffd622c1bc0 sp 0x7ffd622c1b68 T0)
>> ==91050==The signal is caused by a READ memory access.
>> #0 0x7f79a8573dcd (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
>> #1 0x5644c6c0266e in nvme_realize ../hw/nvme/ctrl.c:9613
>> #2 0x5644c6c67213 in pci_qdev_realize ../hw/pci/pci.c:2316
>> #3 0x5644c7a2cfc1 in device_set_realized ../hw/core/qdev.c:514
>> #4 0x5644c7a4f767 in property_set_bool ../qom/object.c:2484
>> #5 0x5644c7a48d0b in object_property_set ../qom/object.c:1548
>> #6 0x5644c7a568a5 in object_property_set_qobject ../qom/qom-qobject.c:28
>> #7 0x5644c7a49385 in object_property_set_bool ../qom/object.c:1618
>> #8 0x5644c7a2aeb0 in qdev_realize ../hw/core/qdev.c:277
>> #9 0x5644c735f29f in qdev_device_add_from_qdict ../system/qdev-monitor.c:740
>> #10 0x5644c735f3ab in qdev_device_add ../system/qdev-monitor.c:758
>> #11 0x5644c72b1901 in device_init_func ../system/vl.c:1217
>> #12 0x5644c829d4a3 in qemu_opts_foreach ../util/qemu-option.c:1148
>> #13 0x5644c72bc33e in qemu_create_cli_devices ../system/vl.c:2762
>> #14 0x5644c72bcaa1 in qmp_x_exit_preconfig ../system/vl.c:2822
>> #15 0x5644c72c3241 in qemu_init ../system/vl.c:3862
>> #16 0x5644c801abf8 in main ../system/main.c:71
>> #17 0x7f79a8427780 (/usr/lib/libc.so.6+0x27780) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
>> #18 0x7f79a84278b8 in __libc_start_main (/usr/lib/libc.so.6+0x278b8) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
>> #19 0x5644c5f0a1f4 in _start (BuildId: 8483f952216d9e345c3744300d0aefa38feb50d7)
>>
>> ==91050==Register values:
>> rax = 0x00007e49988640f0 rbx = 0x00007e49988640f0 rcx = 0x00000fc9b3104828 rdx = 0x0000000000000058
>> rdi = 0x00007e49988640f0 rsi = 0x0000000000001cf0 rbp = 0x00007ffd622c1bc0 rsp = 0x00007ffd622c1b68
>> r8 = 0x00000fc9b3104829 r9 = 0x00000fc9b3104828 r10 = 0x00000fc9b310481e r11 = 0x00000fc9b310481e
>> r12 = 0x0000000000001cf0 r13 = 0x00000f6f32e78578 r14 = 0x00000000ffffffff r15 = 0x00007ffd622c1c10
>> AddressSanitizer can not provide additional info.
>> SUMMARY: AddressSanitizer: SEGV (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
>> ==91050==ABORTING
>>
>> Cc: qemu-stable@nongnu.org
>> Fixes: 19e55471d4e8 ("pcie_sriov: Allow user to create SR-IOV device")
>> Signed-off-by: Daniel Paziyski <danielpaziyski@gmail.com>
>> ---
>> hw/pci/pci.c | 11 ++++++-----
>> hw/pci/pcie_sriov.c | 6 ------
>> 2 files changed, 6 insertions(+), 11 deletions(-)
>>
>> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
>> index d3191609e2..a5b4482bb6 100644
>> --- a/hw/pci/pci.c
>> +++ b/hw/pci/pci.c
>> @@ -2312,20 +2312,21 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
>> if (pci_dev == NULL)
>> return;
>>
>> + if (!pcie_sriov_register_device(pci_dev, errp)) {
>> + do_pci_unregister_device(pci_dev);
>
>
> This skips acpi-index rollback which pci_qdev_unrealize currently does.
> Needs generic PCI cleanup.
I see. pci_qdev_unrealize unregisters the device's acpi-index after calling
do_pci_unregister_device. What do you think if I moved the snippet for
unregistering the acpi-index to a new function, and then call it in
do_pci_unregister_device?
Moreover, this would fix the fact that in do_pci_register_device and outside of
it the acpi-index is not released in case of failure, since this new function
could then be called if necessary, if do_pci_unregister_device is not called.
Additionally, while I'm at it, why don't I move pcie_sriov_unregister_device to
do_pci_unregister_device? This way, I avoid calling it explicitly in
pci_qdev_realize, which is necessary now because user created VFs are registered
before realization.
Regards,
Daniel
>
>
>> + return;
>> + }
>> +
>> if (pc->realize) {
>> pc->realize(pci_dev, &local_err);
>> if (local_err) {
>> error_propagate(errp, local_err);
>> + pcie_sriov_unregister_device(pci_dev);
>> do_pci_unregister_device(pci_dev);
>> return;
>> }
>> }
>>
>> - if (!pcie_sriov_register_device(pci_dev, errp)) {
>> - pci_qdev_unrealize(DEVICE(pci_dev));
>> - return;
>> - }
>> -
>> /*
>> * A PCIe Downstream Port that do not have ARI Forwarding enabled must
>> * associate only Device 0 with the device attached to the bus
>> diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
>> index c41ac95bee..69930c7b8c 100644
>> --- a/hw/pci/pcie_sriov.c
>> +++ b/hw/pci/pcie_sriov.c
>> @@ -357,12 +357,6 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
>>
>> bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
>> {
>> - if (!dev->exp.sriov_pf.vf && dev->qdev.id &&
>> - pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
>> - error_setg(errp, "attaching user-created SR-IOV VF unsupported");
>> - return false;
>> - }
>> -
>> if (dev->sriov_pf) {
>> PCIDevice *pci_pf;
>> GPtrArray *pf;
>> --
>> 2.55.0
>
On Tue, Sep 01, 2026 at 03:24:08PM +0200, Daniel Paziyski wrote:
> On Tue, 1 Sept 2026 at 13:19, Michael S. Tsirkin <mst@redhat.com> wrote:
> >
> > On Wed, Aug 05, 2026 at 02:45:18PM +0200, Daniel Paziyski wrote:
> >> There are two ways of creating virtual functions: by using the sriov-pf device
> >> parameter (this way, creating a user created VF and binding it to a PF), or
> >> by using a device specific parameter, where the device manually creates a given
> >> amount of VFs.
> >>
> >> When a PCI device is realized, the device specific realize function is called
> >> first, and then the pcie_sriov_register_device function is called, which checks
> >> whether the device that has been created is a user created VF, and if it is the
> >> case and the device allows this kind of VFs, it inserts it into a hashmap, with
> >> the key being the ID of the PF, and the items being arrays of VFs.
> >>
> >> User created VFs are instantiated independently, and later, when the PF calls
> >> pcie_sriov_pf_init_from_user_created_vfs, it discovers its VFs from the hashmap
> >> mentioned previously, and sets up in their PCIDevice.ex.sriov_pf structure
> >> the pointer to the PF. This means that, during realization, VFs have no access
> >> to the PF.
> >>
> >> Device created VFs are instantiated during or after PF realization using the
> >> pcie_sriov_pf_init function, which sets up for the VFs the pointer to the PF
> >> before their realization, so when they're realized, they can access the PF
> >> with no issues.
> >>
> >> The problem here is that pcie_sriov_register_device is called after the
> >> realization, and not before. This means that when a user created VF is created
> >> for a device which does not support user created VFs, but supports device
> >> created VFs, the realize function will notice that a VF is being created, and
> >> may try to access the PF, causing a null pointer dereference fault.
> >>
> >> Fix this by placing the user created VF check and registering before the
> >> realization. This way, incorrectly created user created VFs will be noticed,
> >> and device creation will be aborted.
> >>
> >> Additionally, remove from the pcie_sriov_register_device function the top
> >> check. It seems that this check is done to error out if the PF failed for some
> >> reason to initialize its list of user created VFs. However, in such situations,
> >> the pcie_sriov_pf_init_from_user_created_vfs function will error during
> >> realization, and it will be caught before the check is done at all. Moreover,
> >> since now pcie_sriov_register_device is called before realization, the check
> >> will always fail for PFs with user created VFs, because the list will be
> >> populated during realization.
> >>
> >> The rest of the function though, correctly errors out if a user created VF
> >> is created for an unsupported device type, if a VF is created for a non-PCIe
> >> device, or if the PF is already instantiated, with now the advantage being
> >> that the check is done before the VF instantiation.
> >>
> >> When instantiating a user created VF for a NVME controller:
> >>
> >> Command line:
> >>
> >> qemu-system-x86_64 -device nvme-subsys,id=subsys0 \
> >> -device nvme,id=vctrl0,sriov-pf=ctrl0,subsys=subsys0 \
> >> -device nvme,id=ctrl0,subsys=subsys0,serial=s
> >>
> >> ASAN splat:
> >>
> >> ../hw/nvme/ctrl.c:9613:28: runtime error: member access within null pointer of type 'struct NvmeCtrl'
> >> AddressSanitizer:DEADLYSIGNAL
> >> =================================================================
> >> ==91050==ERROR: AddressSanitizer: SEGV on unknown address 0x000000001cf0 (pc 0x7f79a8573dcd bp 0x7ffd622c1bc0 sp 0x7ffd622c1b68 T0)
> >> ==91050==The signal is caused by a READ memory access.
> >> #0 0x7f79a8573dcd (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> >> #1 0x5644c6c0266e in nvme_realize ../hw/nvme/ctrl.c:9613
> >> #2 0x5644c6c67213 in pci_qdev_realize ../hw/pci/pci.c:2316
> >> #3 0x5644c7a2cfc1 in device_set_realized ../hw/core/qdev.c:514
> >> #4 0x5644c7a4f767 in property_set_bool ../qom/object.c:2484
> >> #5 0x5644c7a48d0b in object_property_set ../qom/object.c:1548
> >> #6 0x5644c7a568a5 in object_property_set_qobject ../qom/qom-qobject.c:28
> >> #7 0x5644c7a49385 in object_property_set_bool ../qom/object.c:1618
> >> #8 0x5644c7a2aeb0 in qdev_realize ../hw/core/qdev.c:277
> >> #9 0x5644c735f29f in qdev_device_add_from_qdict ../system/qdev-monitor.c:740
> >> #10 0x5644c735f3ab in qdev_device_add ../system/qdev-monitor.c:758
> >> #11 0x5644c72b1901 in device_init_func ../system/vl.c:1217
> >> #12 0x5644c829d4a3 in qemu_opts_foreach ../util/qemu-option.c:1148
> >> #13 0x5644c72bc33e in qemu_create_cli_devices ../system/vl.c:2762
> >> #14 0x5644c72bcaa1 in qmp_x_exit_preconfig ../system/vl.c:2822
> >> #15 0x5644c72c3241 in qemu_init ../system/vl.c:3862
> >> #16 0x5644c801abf8 in main ../system/main.c:71
> >> #17 0x7f79a8427780 (/usr/lib/libc.so.6+0x27780) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> >> #18 0x7f79a84278b8 in __libc_start_main (/usr/lib/libc.so.6+0x278b8) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> >> #19 0x5644c5f0a1f4 in _start (BuildId: 8483f952216d9e345c3744300d0aefa38feb50d7)
> >>
> >> ==91050==Register values:
> >> rax = 0x00007e49988640f0 rbx = 0x00007e49988640f0 rcx = 0x00000fc9b3104828 rdx = 0x0000000000000058
> >> rdi = 0x00007e49988640f0 rsi = 0x0000000000001cf0 rbp = 0x00007ffd622c1bc0 rsp = 0x00007ffd622c1b68
> >> r8 = 0x00000fc9b3104829 r9 = 0x00000fc9b3104828 r10 = 0x00000fc9b310481e r11 = 0x00000fc9b310481e
> >> r12 = 0x0000000000001cf0 r13 = 0x00000f6f32e78578 r14 = 0x00000000ffffffff r15 = 0x00007ffd622c1c10
> >> AddressSanitizer can not provide additional info.
> >> SUMMARY: AddressSanitizer: SEGV (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
> >> ==91050==ABORTING
> >>
> >> Cc: qemu-stable@nongnu.org
> >> Fixes: 19e55471d4e8 ("pcie_sriov: Allow user to create SR-IOV device")
> >> Signed-off-by: Daniel Paziyski <danielpaziyski@gmail.com>
> >> ---
> >> hw/pci/pci.c | 11 ++++++-----
> >> hw/pci/pcie_sriov.c | 6 ------
> >> 2 files changed, 6 insertions(+), 11 deletions(-)
> >>
> >> diff --git a/hw/pci/pci.c b/hw/pci/pci.c
> >> index d3191609e2..a5b4482bb6 100644
> >> --- a/hw/pci/pci.c
> >> +++ b/hw/pci/pci.c
> >> @@ -2312,20 +2312,21 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
> >> if (pci_dev == NULL)
> >> return;
> >>
> >> + if (!pcie_sriov_register_device(pci_dev, errp)) {
> >> + do_pci_unregister_device(pci_dev);
> >
> >
> > This skips acpi-index rollback which pci_qdev_unrealize currently does.
> > Needs generic PCI cleanup.
>
> I see. pci_qdev_unrealize unregisters the device's acpi-index after calling
> do_pci_unregister_device. What do you think if I moved the snippet for
> unregistering the acpi-index to a new function, and then call it in
> do_pci_unregister_device?
>
> Moreover, this would fix the fact that in do_pci_register_device and outside of
> it the acpi-index is not released in case of failure, since this new function
> could then be called if necessary, if do_pci_unregister_device is not called.
>
> Additionally, while I'm at it, why don't I move pcie_sriov_unregister_device to
> do_pci_unregister_device? This way, I avoid calling it explicitly in
> pci_qdev_realize, which is necessary now because user created VFs are registered
> before realization.
>
> Regards,
> Daniel
Hard to say like that pls send a patch.
> >
> >
> >> + return;
> >> + }
> >> +
> >> if (pc->realize) {
> >> pc->realize(pci_dev, &local_err);
> >> if (local_err) {
> >> error_propagate(errp, local_err);
> >> + pcie_sriov_unregister_device(pci_dev);
> >> do_pci_unregister_device(pci_dev);
> >> return;
> >> }
> >> }
> >>
> >> - if (!pcie_sriov_register_device(pci_dev, errp)) {
> >> - pci_qdev_unrealize(DEVICE(pci_dev));
> >> - return;
> >> - }
> >> -
> >> /*
> >> * A PCIe Downstream Port that do not have ARI Forwarding enabled must
> >> * associate only Device 0 with the device attached to the bus
> >> diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
> >> index c41ac95bee..69930c7b8c 100644
> >> --- a/hw/pci/pcie_sriov.c
> >> +++ b/hw/pci/pcie_sriov.c
> >> @@ -357,12 +357,6 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
> >>
> >> bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
> >> {
> >> - if (!dev->exp.sriov_pf.vf && dev->qdev.id &&
> >> - pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
> >> - error_setg(errp, "attaching user-created SR-IOV VF unsupported");
> >> - return false;
> >> - }
> >> -
> >> if (dev->sriov_pf) {
> >> PCIDevice *pci_pf;
> >> GPtrArray *pf;
> >> --
> >> 2.55.0
> >
There are two ways of creating virtual functions: by using the sriov-pf device
parameter (this way, creating a user created VF and binding it to a PF), or
by using a device specific parameter, where the device manually creates a given
amount of VFs.
When a PCI device is realized, the device specific realize function is called
first, and then the pcie_sriov_register_device function is called, which checks
whether the device that has been created is a user created VF, and if it is the
case and the device allows this kind of VFs, it inserts it into a hashmap, with
the key being the ID of the PF, and the items being arrays of VFs.
User created VFs are instantiated independently, and later, when the PF calls
pcie_sriov_pf_init_from_user_created_vfs, it discovers its VFs from the hashmap
mentioned previously, and sets up in their PCIDevice.ex.sriov_pf structure
the pointer to the PF. This means that, during realization, VFs have no access
to the PF.
Device created VFs are instantiated during or after PF realization using the
pcie_sriov_pf_init function, which sets up for the VFs the pointer to the PF
before their realization, so when they're realized, they can access the PF
with no issues.
The problem here is that pcie_sriov_register_device is called after the
realization, and not before. This means that when a user created VF is created
for a device which does not support user created VFs, but supports device
created VFs, the realize function will notice that a VF is being created, and
may try to access the PF, causing a null pointer dereference fault.
Fix this by placing the user created VF check and registering before the
realization. This way, incorrectly created user created VFs will be noticed,
and device creation will be aborted.
Additionally, remove from the pcie_sriov_register_device function the top
check. It seems that this check is done to error out if the PF failed for some
reason to initialize its list of user created VFs. However, in such situations,
the pcie_sriov_pf_init_from_user_created_vfs function will error during
realization, and it will be caught before the check is done at all. Moreover,
since now pcie_sriov_register_device is called before realization, the check
will always fail for PFs with user created VFs, because the list will be
populated during realization.
The rest of the function though, correctly errors out if a user created VF
is created for an unsupported device type, if a VF is created for a non-PCIe
device, or if the PF is already instantiated, with now the advantage being
that the check is done before the VF instantiation.
Moreover, move the unregistering of a device's acpi-index and the removal
of a VF from its PF list from pci_qdev_unrealize to do_pci_unregister_device.
We do the former so that the acpi-index is unclaimed on user created VF
creation error, and the latter to not have extra code on the device specific
realization error path.
When instantiating a user created VF for a NVME controller:
Command line:
qemu-system-x86_64 -device nvme-subsys,id=subsys0 \
-device nvme,id=vctrl0,sriov-pf=ctrl0,subsys=subsys0 \
-device nvme,id=ctrl0,subsys=subsys0,serial=s
ASAN splat:
../hw/nvme/ctrl.c:9613:28: runtime error: member access within null pointer of type 'struct NvmeCtrl'
AddressSanitizer:DEADLYSIGNAL
=================================================================
==91050==ERROR: AddressSanitizer: SEGV on unknown address 0x000000001cf0 (pc 0x7f79a8573dcd bp 0x7ffd622c1bc0 sp 0x7ffd622c1b68 T0)
==91050==The signal is caused by a READ memory access.
#0 0x7f79a8573dcd (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
#1 0x5644c6c0266e in nvme_realize ../hw/nvme/ctrl.c:9613
#2 0x5644c6c67213 in pci_qdev_realize ../hw/pci/pci.c:2316
#3 0x5644c7a2cfc1 in device_set_realized ../hw/core/qdev.c:514
#4 0x5644c7a4f767 in property_set_bool ../qom/object.c:2484
#5 0x5644c7a48d0b in object_property_set ../qom/object.c:1548
#6 0x5644c7a568a5 in object_property_set_qobject ../qom/qom-qobject.c:28
#7 0x5644c7a49385 in object_property_set_bool ../qom/object.c:1618
#8 0x5644c7a2aeb0 in qdev_realize ../hw/core/qdev.c:277
#9 0x5644c735f29f in qdev_device_add_from_qdict ../system/qdev-monitor.c:740
#10 0x5644c735f3ab in qdev_device_add ../system/qdev-monitor.c:758
#11 0x5644c72b1901 in device_init_func ../system/vl.c:1217
#12 0x5644c829d4a3 in qemu_opts_foreach ../util/qemu-option.c:1148
#13 0x5644c72bc33e in qemu_create_cli_devices ../system/vl.c:2762
#14 0x5644c72bcaa1 in qmp_x_exit_preconfig ../system/vl.c:2822
#15 0x5644c72c3241 in qemu_init ../system/vl.c:3862
#16 0x5644c801abf8 in main ../system/main.c:71
#17 0x7f79a8427780 (/usr/lib/libc.so.6+0x27780) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
#18 0x7f79a84278b8 in __libc_start_main (/usr/lib/libc.so.6+0x278b8) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
#19 0x5644c5f0a1f4 in _start (BuildId: 8483f952216d9e345c3744300d0aefa38feb50d7)
==91050==Register values:
rax = 0x00007e49988640f0 rbx = 0x00007e49988640f0 rcx = 0x00000fc9b3104828 rdx = 0x0000000000000058
rdi = 0x00007e49988640f0 rsi = 0x0000000000001cf0 rbp = 0x00007ffd622c1bc0 rsp = 0x00007ffd622c1b68
r8 = 0x00000fc9b3104829 r9 = 0x00000fc9b3104828 r10 = 0x00000fc9b310481e r11 = 0x00000fc9b310481e
r12 = 0x0000000000001cf0 r13 = 0x00000f6f32e78578 r14 = 0x00000000ffffffff r15 = 0x00007ffd622c1c10
AddressSanitizer can not provide additional info.
SUMMARY: AddressSanitizer: SEGV (/usr/lib/libc.so.6+0x173dcd) (BuildId: 1fa174a830cef40a5b2388add4318ee2795f573e)
==91050==ABORTING
Cc: qemu-stable@nongnu.org
Fixes: 19e55471d4e8 ("pcie_sriov: Allow user to create SR-IOV device")
Signed-off-by: Daniel Paziyski <danielpaziyski@gmail.com>
---
Before I make a v2, I send the patch over here to show you what I had in mind.
hw/pci/pci.c | 42 ++++++++++++++++++++++++------------------
hw/pci/pcie_sriov.c | 6 ------
2 files changed, 24 insertions(+), 24 deletions(-)
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index e8e8a3b767..58fe913b85 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -1221,6 +1221,19 @@ static void pci_config_free(PCIDevice *pci_dev)
g_free(pci_dev->used);
}
+static void pci_unregister_acpi_index(PCIDevice *pci_dev)
+{
+ if (pci_dev->acpi_index) {
+ GSequence *used_indexes = pci_acpi_index_list();
+
+ g_sequence_remove(g_sequence_lookup(used_indexes,
+ GINT_TO_POINTER(pci_dev->acpi_index),
+ g_cmp_uint32, NULL));
+
+ pci_dev->acpi_index = 0;
+ }
+}
+
static void do_pci_unregister_device(PCIDevice *pci_dev)
{
pci_get_bus(pci_dev)->devices[pci_dev->devfn] = NULL;
@@ -1234,6 +1247,9 @@ static void do_pci_unregister_device(PCIDevice *pci_dev)
&pci_dev->bus_master_enable_region);
}
address_space_destroy(&pci_dev->bus_master_as);
+
+ pcie_sriov_unregister_device(pci_dev);
+ pci_unregister_acpi_index(pci_dev);
}
/* Extract PCIReqIDCache into BDF format */
@@ -1485,7 +1501,6 @@ static void pci_qdev_unrealize(DeviceState *dev)
pci_unregister_io_regions(pci_dev);
pci_del_option_rom(pci_dev);
- pcie_sriov_unregister_device(pci_dev);
if (pc->exit) {
pc->exit(pci_dev);
@@ -1495,17 +1510,6 @@ static void pci_qdev_unrealize(DeviceState *dev)
do_pci_unregister_device(pci_dev);
pci_dev->msi_trigger = NULL;
-
- /*
- * clean up acpi-index so it could reused by another device
- */
- if (pci_dev->acpi_index) {
- GSequence *used_indexes = pci_acpi_index_list();
-
- g_sequence_remove(g_sequence_lookup(used_indexes,
- GINT_TO_POINTER(pci_dev->acpi_index),
- g_cmp_uint32, NULL));
- }
}
void pci_register_bar(PCIDevice *pci_dev, int region_num,
@@ -2316,8 +2320,15 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
pci_dev = do_pci_register_device(pci_dev,
object_get_typename(OBJECT(qdev)),
pci_dev->devfn, errp);
- if (pci_dev == NULL)
+ if (pci_dev == NULL) {
+ pci_unregister_acpi_index(pci_dev);
return;
+ }
+
+ if (!pcie_sriov_register_device(pci_dev, errp)) {
+ do_pci_unregister_device(pci_dev);
+ return;
+ }
if (pc->realize) {
pc->realize(pci_dev, &local_err);
@@ -2328,11 +2339,6 @@ static void pci_qdev_realize(DeviceState *qdev, Error **errp)
}
}
- if (!pcie_sriov_register_device(pci_dev, errp)) {
- pci_qdev_unrealize(DEVICE(pci_dev));
- return;
- }
-
/*
* A PCIe Downstream Port that do not have ARI Forwarding enabled must
* associate only Device 0 with the device attached to the bus
diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c
index c41ac95bee..69930c7b8c 100644
--- a/hw/pci/pcie_sriov.c
+++ b/hw/pci/pcie_sriov.c
@@ -357,12 +357,6 @@ int16_t pcie_sriov_pf_init_from_user_created_vfs(PCIDevice *dev,
bool pcie_sriov_register_device(PCIDevice *dev, Error **errp)
{
- if (!dev->exp.sriov_pf.vf && dev->qdev.id &&
- pfs && g_hash_table_contains(pfs, dev->qdev.id)) {
- error_setg(errp, "attaching user-created SR-IOV VF unsupported");
- return false;
- }
-
if (dev->sriov_pf) {
PCIDevice *pci_pf;
GPtrArray *pf;
--
2.55.0© 2016 - 2026 Red Hat, Inc.