[PATCH v3 0/2] pcie: Fix ARI next function numbers

[PATCH v3 0/2] pcie: Fix ARI next function numbers

[Akihiko Odaki]

The ARI next function number field is undefined for VF. The PF should
end the linked list formed with the field by specifying 0.

Supersedes: <20230701070133.24877-1-akihiko.odaki@daynix.com>
("[PATCH 0/4] pci: Compare function number and ARI next function number")

V2 -> V3:
  Moved the logic to PCI common infrastucture (Michael S. Tsirkin)

V1 -> V2:
  Fixed migration. (Michael S. Tsirkin)
  Added a caveat comment. (Michael S. Tsirkin)

Akihiko Odaki (2):
  pcie: Use common ARI next function number
  pcie: Specify 0 for ARI next function numbers

 docs/pcie_sriov.txt   | 4 ++--
 include/hw/pci/pci.h  | 2 ++
 include/hw/pci/pcie.h | 2 +-
 hw/core/machine.c     | 1 +
 hw/net/igb.c          | 2 +-
 hw/net/igbvf.c        | 2 +-
 hw/nvme/ctrl.c        | 2 +-
 hw/pci/pci.c          | 2 ++
 hw/pci/pcie.c         | 4 +++-
 9 files changed, 14 insertions(+), 7 deletions(-)

-- 
2.41.0

[PATCH v3 1/2] pcie: Use common ARI next function number

[Akihiko Odaki]

Currently the only implementers of ARI is SR-IOV devices, and they
behave similar. Share the ARI next function number.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 docs/pcie_sriov.txt   | 4 ++--
 include/hw/pci/pcie.h | 2 +-
 hw/net/igb.c          | 2 +-
 hw/net/igbvf.c        | 2 +-
 hw/nvme/ctrl.c        | 2 +-
 hw/pci/pcie.c         | 4 +++-
 6 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/docs/pcie_sriov.txt b/docs/pcie_sriov.txt
index 7eff7f2703..a47aad0bfa 100644
--- a/docs/pcie_sriov.txt
+++ b/docs/pcie_sriov.txt
@@ -48,7 +48,7 @@ setting up a BAR for a VF.
       ...
       int ret = pcie_endpoint_cap_init(d, 0x70);
       ...
-      pcie_ari_init(d, 0x100, 1);
+      pcie_ari_init(d, 0x100);
       ...
 
       /* Add and initialize the SR/IOV capability */
@@ -78,7 +78,7 @@ setting up a BAR for a VF.
       ...
       int ret = pcie_endpoint_cap_init(d, 0x60);
       ...
-      pcie_ari_init(d, 0x100, 1);
+      pcie_ari_init(d, 0x100);
       ...
       memory_region_init(mr, ... )
       pcie_sriov_vf_register_bar(d, bar_nr, mr);
diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h
index 3cc2b15957..bf7dc5d685 100644
--- a/include/hw/pci/pcie.h
+++ b/include/hw/pci/pcie.h
@@ -134,7 +134,7 @@ void pcie_sync_bridge_lnk(PCIDevice *dev);
 void pcie_acs_init(PCIDevice *dev, uint16_t offset);
 void pcie_acs_reset(PCIDevice *dev);
 
-void pcie_ari_init(PCIDevice *dev, uint16_t offset, uint16_t nextfn);
+void pcie_ari_init(PCIDevice *dev, uint16_t offset);
 void pcie_dev_ser_num_init(PCIDevice *dev, uint16_t offset, uint64_t ser_num);
 void pcie_ats_init(PCIDevice *dev, uint16_t offset, bool aligned);
 
diff --git a/hw/net/igb.c b/hw/net/igb.c
index 1c989d7677..8ff832acfc 100644
--- a/hw/net/igb.c
+++ b/hw/net/igb.c
@@ -431,7 +431,7 @@ static void igb_pci_realize(PCIDevice *pci_dev, Error **errp)
         hw_error("Failed to initialize AER capability");
     }
 
-    pcie_ari_init(pci_dev, 0x150, 1);
+    pcie_ari_init(pci_dev, 0x150);
 
     pcie_sriov_pf_init(pci_dev, IGB_CAP_SRIOV_OFFSET, TYPE_IGBVF,
         IGB_82576_VF_DEV_ID, IGB_MAX_VF_FUNCTIONS, IGB_MAX_VF_FUNCTIONS,
diff --git a/hw/net/igbvf.c b/hw/net/igbvf.c
index 284ea61184..d55e1e8a6a 100644
--- a/hw/net/igbvf.c
+++ b/hw/net/igbvf.c
@@ -270,7 +270,7 @@ static void igbvf_pci_realize(PCIDevice *dev, Error **errp)
         hw_error("Failed to initialize AER capability");
     }
 
-    pcie_ari_init(dev, 0x150, 1);
+    pcie_ari_init(dev, 0x150);
 }
 
 static void igbvf_pci_uninit(PCIDevice *dev)
diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c
index fd917fcda1..8b7168a266 100644
--- a/hw/nvme/ctrl.c
+++ b/hw/nvme/ctrl.c
@@ -8088,7 +8088,7 @@ static bool nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev, Error **errp)
     pcie_endpoint_cap_init(pci_dev, 0x80);
     pcie_cap_flr_init(pci_dev);
     if (n->params.sriov_max_vfs) {
-        pcie_ari_init(pci_dev, 0x100, 1);
+        pcie_ari_init(pci_dev, 0x100);
     }
 
     /* add one to max_ioqpairs to account for the admin queue pair */
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index b8c24cf45f..9a3f6430e8 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -1028,8 +1028,10 @@ void pcie_sync_bridge_lnk(PCIDevice *bridge_dev)
  */
 
 /* ARI */
-void pcie_ari_init(PCIDevice *dev, uint16_t offset, uint16_t nextfn)
+void pcie_ari_init(PCIDevice *dev, uint16_t offset)
 {
+    uint16_t nextfn = 1;
+
     pcie_add_capability(dev, PCI_EXT_CAP_ID_ARI, PCI_ARI_VER,
                         offset, PCI_ARI_SIZEOF);
     pci_set_long(dev->config + offset + PCI_ARI_CAP, (nextfn & 0xff) << 8);
-- 
2.41.0

[PATCH v3 2/2] pcie: Specify 0 for ARI next function numbers

[Akihiko Odaki]

The current implementers of ARI are all SR-IOV devices. The ARI next
function number field is undefined for VF. The PF should end the linked
list formed with the field by specifying 0.

Fixes: 2503461691 ("pcie: Add some SR/IOV API documentation in docs/pcie_sriov.txt")
Fixes: 44c2c09488 ("hw/nvme: Add support for SR-IOV")
Fixes: 3a977deebe ("Intrdocue igb device emulation")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
---
 include/hw/pci/pci.h | 2 ++
 hw/core/machine.c    | 1 +
 hw/pci/pci.c         | 2 ++
 hw/pci/pcie.c        | 2 +-
 4 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
index e6d0574a29..9c5b5eb206 100644
--- a/include/hw/pci/pci.h
+++ b/include/hw/pci/pci.h
@@ -209,6 +209,8 @@ enum {
     QEMU_PCIE_CAP_CXL = (1 << QEMU_PCIE_CXL_BITNR),
 #define QEMU_PCIE_ERR_UNC_MASK_BITNR 11
     QEMU_PCIE_ERR_UNC_MASK = (1 << QEMU_PCIE_ERR_UNC_MASK_BITNR),
+#define QEMU_PCIE_ARI_NEXTFN_1_BITNR 12
+    QEMU_PCIE_ARI_NEXTFN_1 = (1 << QEMU_PCIE_ARI_NEXTFN_1_BITNR),
 };
 
 typedef struct PCIINTxRoute {
diff --git a/hw/core/machine.c b/hw/core/machine.c
index 46f8f9a2b0..f0d35c6401 100644
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -41,6 +41,7 @@
 
 GlobalProperty hw_compat_8_0[] = {
     { "migration", "multifd-flush-after-each-section", "on"},
+    { TYPE_PCI_DEVICE, "x-pcie-ari-nextfn-1", "on" },
 };
 const size_t hw_compat_8_0_len = G_N_ELEMENTS(hw_compat_8_0);
 
diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index e2eb4c3b4a..f2ce1dbfd0 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -82,6 +82,8 @@ static Property pci_props[] = {
     DEFINE_PROP_UINT32("acpi-index",  PCIDevice, acpi_index, 0),
     DEFINE_PROP_BIT("x-pcie-err-unc-mask", PCIDevice, cap_present,
                     QEMU_PCIE_ERR_UNC_MASK_BITNR, true),
+    DEFINE_PROP_BIT("x-pcie-ari-nextfn-1", PCIDevice, cap_present,
+                    QEMU_PCIE_ARI_NEXTFN_1_BITNR, true),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
index 9a3f6430e8..cf09e03a10 100644
--- a/hw/pci/pcie.c
+++ b/hw/pci/pcie.c
@@ -1030,7 +1030,7 @@ void pcie_sync_bridge_lnk(PCIDevice *bridge_dev)
 /* ARI */
 void pcie_ari_init(PCIDevice *dev, uint16_t offset)
 {
-    uint16_t nextfn = 1;
+    uint16_t nextfn = dev->cap_present & QEMU_PCIE_ARI_NEXTFN_1 ? 1 : 0;
 
     pcie_add_capability(dev, PCI_EXT_CAP_ID_ARI, PCI_ARI_VER,
                         offset, PCI_ARI_SIZEOF);
-- 
2.41.0

Re: [PATCH v3 0/2] pcie: Fix ARI next function numbers

[Michael S. Tsirkin]

On Sun, Jul 02, 2023 at 09:02:25PM +0900, Akihiko Odaki wrote:
> The ARI next function number field is undefined for VF. The PF should
> end the linked list formed with the field by specifying 0.
> 
> Supersedes: <20230701070133.24877-1-akihiko.odaki@daynix.com>
> ("[PATCH 0/4] pci: Compare function number and ARI next function number")

Thanks! How was this patch tested?


> V2 -> V3:
>   Moved the logic to PCI common infrastucture (Michael S. Tsirkin)
> 
> V1 -> V2:
>   Fixed migration. (Michael S. Tsirkin)
>   Added a caveat comment. (Michael S. Tsirkin)
> 
> Akihiko Odaki (2):
>   pcie: Use common ARI next function number
>   pcie: Specify 0 for ARI next function numbers
> 
>  docs/pcie_sriov.txt   | 4 ++--
>  include/hw/pci/pci.h  | 2 ++
>  include/hw/pci/pcie.h | 2 +-
>  hw/core/machine.c     | 1 +
>  hw/net/igb.c          | 2 +-
>  hw/net/igbvf.c        | 2 +-
>  hw/nvme/ctrl.c        | 2 +-
>  hw/pci/pci.c          | 2 ++
>  hw/pci/pcie.c         | 4 +++-
>  9 files changed, 14 insertions(+), 7 deletions(-)
> 
> -- 
> 2.41.0

Re: [PATCH v3 0/2] pcie: Fix ARI next function numbers

[Akihiko Odaki]

On 2023/07/02 21:43, Michael S. Tsirkin wrote:
> On Sun, Jul 02, 2023 at 09:02:25PM +0900, Akihiko Odaki wrote:
>> The ARI next function number field is undefined for VF. The PF should
>> end the linked list formed with the field by specifying 0.
>>
>> Supersedes: <20230701070133.24877-1-akihiko.odaki@daynix.com>
>> ("[PATCH 0/4] pci: Compare function number and ARI next function number")
> 
> Thanks! How was this patch tested?

I brought VFs up with igb and performed link up for a fresh VM and a VM 
migrated from 8.0.2.

> 
> 
>> V2 -> V3:
>>    Moved the logic to PCI common infrastucture (Michael S. Tsirkin)
>>
>> V1 -> V2:
>>    Fixed migration. (Michael S. Tsirkin)
>>    Added a caveat comment. (Michael S. Tsirkin)
>>
>> Akihiko Odaki (2):
>>    pcie: Use common ARI next function number
>>    pcie: Specify 0 for ARI next function numbers
>>
>>   docs/pcie_sriov.txt   | 4 ++--
>>   include/hw/pci/pci.h  | 2 ++
>>   include/hw/pci/pcie.h | 2 +-
>>   hw/core/machine.c     | 1 +
>>   hw/net/igb.c          | 2 +-
>>   hw/net/igbvf.c        | 2 +-
>>   hw/nvme/ctrl.c        | 2 +-
>>   hw/pci/pci.c          | 2 ++
>>   hw/pci/pcie.c         | 4 +++-
>>   9 files changed, 14 insertions(+), 7 deletions(-)
>>
>> -- 
>> 2.41.0
> 

Re: [PATCH v3 0/2] pcie: Fix ARI next function numbers

[Michael S. Tsirkin]

On Mon, Jul 03, 2023 at 12:17:16PM +0900, Akihiko Odaki wrote:
> On 2023/07/02 21:43, Michael S. Tsirkin wrote:
> > On Sun, Jul 02, 2023 at 09:02:25PM +0900, Akihiko Odaki wrote:
> > > The ARI next function number field is undefined for VF. The PF should
> > > end the linked list formed with the field by specifying 0.
> > > 
> > > Supersedes: <20230701070133.24877-1-akihiko.odaki@daynix.com>
> > > ("[PATCH 0/4] pci: Compare function number and ARI next function number")
> > 
> > Thanks! How was this patch tested?
> 
> I brought VFs up with igb and performed link up for a fresh VM and a VM
> migrated from 8.0.2.

Which guest?

> > 
> > 
> > > V2 -> V3:
> > >    Moved the logic to PCI common infrastucture (Michael S. Tsirkin)
> > > 
> > > V1 -> V2:
> > >    Fixed migration. (Michael S. Tsirkin)
> > >    Added a caveat comment. (Michael S. Tsirkin)
> > > 
> > > Akihiko Odaki (2):
> > >    pcie: Use common ARI next function number
> > >    pcie: Specify 0 for ARI next function numbers
> > > 
> > >   docs/pcie_sriov.txt   | 4 ++--
> > >   include/hw/pci/pci.h  | 2 ++
> > >   include/hw/pci/pcie.h | 2 +-
> > >   hw/core/machine.c     | 1 +
> > >   hw/net/igb.c          | 2 +-
> > >   hw/net/igbvf.c        | 2 +-
> > >   hw/nvme/ctrl.c        | 2 +-
> > >   hw/pci/pci.c          | 2 ++
> > >   hw/pci/pcie.c         | 4 +++-
> > >   9 files changed, 14 insertions(+), 7 deletions(-)
> > > 
> > > -- 
> > > 2.41.0
> > 

Re: [PATCH v3 0/2] pcie: Fix ARI next function numbers

[Akihiko Odaki]

On 2023/07/03 13:52, Michael S. Tsirkin wrote:
> On Mon, Jul 03, 2023 at 12:17:16PM +0900, Akihiko Odaki wrote:
>> On 2023/07/02 21:43, Michael S. Tsirkin wrote:
>>> On Sun, Jul 02, 2023 at 09:02:25PM +0900, Akihiko Odaki wrote:
>>>> The ARI next function number field is undefined for VF. The PF should
>>>> end the linked list formed with the field by specifying 0.
>>>>
>>>> Supersedes: <20230701070133.24877-1-akihiko.odaki@daynix.com>
>>>> ("[PATCH 0/4] pci: Compare function number and ARI next function number")
>>>
>>> Thanks! How was this patch tested?
>>
>> I brought VFs up with igb and performed link up for a fresh VM and a VM
>> migrated from 8.0.2.
> 
> Which guest?

I use Fedora 38.

> 
>>>
>>>
>>>> V2 -> V3:
>>>>     Moved the logic to PCI common infrastucture (Michael S. Tsirkin)
>>>>
>>>> V1 -> V2:
>>>>     Fixed migration. (Michael S. Tsirkin)
>>>>     Added a caveat comment. (Michael S. Tsirkin)
>>>>
>>>> Akihiko Odaki (2):
>>>>     pcie: Use common ARI next function number
>>>>     pcie: Specify 0 for ARI next function numbers
>>>>
>>>>    docs/pcie_sriov.txt   | 4 ++--
>>>>    include/hw/pci/pci.h  | 2 ++
>>>>    include/hw/pci/pcie.h | 2 +-
>>>>    hw/core/machine.c     | 1 +
>>>>    hw/net/igb.c          | 2 +-
>>>>    hw/net/igbvf.c        | 2 +-
>>>>    hw/nvme/ctrl.c        | 2 +-
>>>>    hw/pci/pci.c          | 2 ++
>>>>    hw/pci/pcie.c         | 4 +++-
>>>>    9 files changed, 14 insertions(+), 7 deletions(-)
>>>>
>>>> -- 
>>>> 2.41.0
>>>
> 

Re: [PATCH v3 2/2] pcie: Specify 0 for ARI next function numbers

[Igor Mammedov]

On Sun,  2 Jul 2023 21:02:27 +0900
Akihiko Odaki <akihiko.odaki@daynix.com> wrote:

> The current implementers of ARI are all SR-IOV devices. The ARI next
> function number field is undefined for VF. The PF should end the linked
> list formed with the field by specifying 0.

this should also describe compat behavior changes.


> Fixes: 2503461691 ("pcie: Add some SR/IOV API documentation in docs/pcie_sriov.txt")
> Fixes: 44c2c09488 ("hw/nvme: Add support for SR-IOV")
> Fixes: 3a977deebe ("Intrdocue igb device emulation")
> Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
> ---
>  include/hw/pci/pci.h | 2 ++
>  hw/core/machine.c    | 1 +
>  hw/pci/pci.c         | 2 ++
>  hw/pci/pcie.c        | 2 +-
>  4 files changed, 6 insertions(+), 1 deletion(-)
> 

>  GlobalProperty hw_compat_8_0[] = {
>      { "migration", "multifd-flush-after-each-section", "on"},
> +    { TYPE_PCI_DEVICE, "x-pcie-ari-nextfn-1", "on" },
>  };

[...]

> +    DEFINE_PROP_BIT("x-pcie-ari-nextfn-1", PCIDevice, cap_present,
> +                    QEMU_PCIE_ARI_NEXTFN_1_BITNR, true),

now, I'm confused a bit. So above line says that default
x-pcie-ari-nextfn-1=on

then compat also sets it to 'on', so question is why do
we have compat entry at all?
If default state doesn't change why do we need involve compat
machinery and add "x-pcie-ari-nextfn-1" property?

>      DEFINE_PROP_END_OF_LIST()
>  };
>  
> diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c
> index 9a3f6430e8..cf09e03a10 100644
> --- a/hw/pci/pcie.c
> +++ b/hw/pci/pcie.c
> @@ -1030,7 +1030,7 @@ void pcie_sync_bridge_lnk(PCIDevice *bridge_dev)
>  /* ARI */
>  void pcie_ari_init(PCIDevice *dev, uint16_t offset)
>  {
> -    uint16_t nextfn = 1;
> +    uint16_t nextfn = dev->cap_present & QEMU_PCIE_ARI_NEXTFN_1 ? 1 : 0;
>  
>      pcie_add_capability(dev, PCI_EXT_CAP_ID_ARI, PCI_ARI_VER,
>                          offset, PCI_ARI_SIZEOF);