Re: [RFC KERNEL PATCH v7 2/2] xen/privcmd: Add new syscall to get gsi from dev
On Thu, 16 May 2024, Chen, Jiqian wrote:
> On 2024/5/16 06:42, Stefano Stabellini wrote:
> > On Wed, 15 May 2024, Jiqian Chen wrote:
> >> In PVH dom0, it uses the linux local interrupt mechanism,
> >> when it allocs irq for a gsi, it is dynamic, and follow
> >> the principle of applying first, distributing first. And
> >> the irq number is alloced from small to large, but the
> >> applying gsi number is not, may gsi 38 comes before gsi 28,
> >> it causes the irq number is not equal with the gsi number.
> >> And when passthrough a device, QEMU will use device's gsi
> >> number to do pirq mapping, but the gsi number is got from
> >> file /sys/bus/pci/devices//irq, irq!= gsi, so it will
> >> fail when mapping.
> >> And in current linux codes, there is no method to get gsi
> >> for userspace.
> >>
> >> For above purpose, record gsi of pcistub devices when init
> >> pcistub and add a new syscall into privcmd to let userspace
> >> can get gsi when they have a need.
> >>
> >> Co-developed-by: Huang Rui
> >> Signed-off-by: Jiqian Chen
> >> ---
> >> drivers/xen/privcmd.c | 28 ++
> >> drivers/xen/xen-pciback/pci_stub.c | 38 +++---
> >> include/uapi/xen/privcmd.h | 7 ++
> >> include/xen/acpi.h | 2 ++
> >> 4 files changed, 72 insertions(+), 3 deletions(-)
> >>
> >> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
> >> index 67dfa4778864..5953a03b5cb0 100644
> >> --- a/drivers/xen/privcmd.c
> >> +++ b/drivers/xen/privcmd.c
> >> @@ -45,6 +45,9 @@
> >> #include
> >> #include
> >> #include
> >> +#ifdef CONFIG_ACPI
> >> +#include
> >> +#endif
> >>
> >> #include "privcmd.h"
> >>
> >> @@ -842,6 +845,27 @@ static long privcmd_ioctl_mmap_resource(struct file
> >> *file,
> >>return rc;
> >> }
> >>
> >> +static long privcmd_ioctl_gsi_from_dev(struct file *file, void __user
> >> *udata)
> >> +{
> >> + struct privcmd_gsi_from_dev kdata;
> >> +
> >> + if (copy_from_user(, udata, sizeof(kdata)))
> >> + return -EFAULT;
> >> +
> >> +#ifdef CONFIG_ACPI
> >> + kdata.gsi = pcistub_get_gsi_from_sbdf(kdata.sbdf);
> >> + if (kdata.gsi == -1)
> >> + return -EINVAL;
> >> +#else
> >> + kdata.gsi = -1;
> >
> > Should we return an error instead, like -EINVAL, to make the behavior
> > more similar to the CONFIG_ACPI case?
> OK, will return -EINVAL if not config acpi.
> Like:
> static long privcmd_ioctl_gsi_from_dev(struct file *file, void __user *udata)
> {
> #ifdef CONFIG_ACPI
> struct privcmd_gsi_from_dev kdata;
>
> if (copy_from_user(, udata, sizeof(kdata)))
> return -EFAULT;
>
> kdata.gsi = pcistub_get_gsi_from_sbdf(kdata.sbdf);
> if (kdata.gsi == -1)
> return -EINVAL;
>
> if (copy_to_user(udata, , sizeof(kdata)))
> return -EFAULT;
>
> return 0;
> #else
> return -EINVAL;
> #endif
> }
Yep that's fine
> >> +#endif
> >> +
> >> + if (copy_to_user(udata, , sizeof(kdata)))
> >> + return -EFAULT;
> >> +
> >> + return 0;
> >> +}
> >> +
> >> #ifdef CONFIG_XEN_PRIVCMD_EVENTFD
> >> /* Irqfd support */
> >> static struct workqueue_struct *irqfd_cleanup_wq;
> >> @@ -1529,6 +1553,10 @@ static long privcmd_ioctl(struct file *file,
> >>ret = privcmd_ioctl_ioeventfd(file, udata);
> >>break;
> >>
> >> + case IOCTL_PRIVCMD_GSI_FROM_DEV:
> >> + ret = privcmd_ioctl_gsi_from_dev(file, udata);
> >> + break;
> >> +
> >>default:
> >>break;
> >>}
> >> diff --git a/drivers/xen/xen-pciback/pci_stub.c
> >> b/drivers/xen/xen-pciback/pci_stub.c
> >> index 2b90d832d0a7..4b62b4d377a9 100644
> >> --- a/drivers/xen/xen-pciback/pci_stub.c
> >> +++ b/drivers/xen/xen-pciback/pci_stub.c
> >> @@ -56,6 +56,9 @@ struct pcistub_device {
> >>
> >>struct pci_dev *dev;
> >>struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
> >> +#ifdef CONFIG_ACPI
> >> + int gsi;
> >> +#endif
> >> };
> >>
> >> /* Access to pcistub_devices & seized_devices lists and the
> >> initialize_devices
> >> @@ -88,6 +91,9 @@ static struct pcistub_device
> >> *pcistub_device_alloc(struct pci_dev *dev)
> >>
> >>kref_init(>kref);
> >>spin_lock_init(>lock);
> >> +#ifdef CONFIG_ACPI
> >> + psdev->gsi = -1;
> >> +#endif
> >>
> >>return psdev;
> >> }
> >> @@ -220,6 +226,25 @@ static struct pci_dev
> >> *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
> >>return pci_dev;
> >> }
> >>
> >> +#ifdef CONFIG_ACPI
> >> +int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
> >> +{
> >> + struct pcistub_device *psdev;
> >> + int domain = sbdf >> 16;
> >> + int bus = (sbdf >> 8) & 0xff;
> >> + int slot = (sbdf >> 3) & 0x1f;
> >> + int func = sbdf & 0x7;
> >
> > you can use PCI_DEVFN PCI_SLOT PCI_FUNC pci_domain_nr instead of open
> > coding.
> Thanks, will change to use these in next version.
> But pci_domain_nr requires passing in
Re: [RFC KERNEL PATCH v7 2/2] xen/privcmd: Add new syscall to get gsi from dev
On 2024/5/16 06:42, Stefano Stabellini wrote:
> On Wed, 15 May 2024, Jiqian Chen wrote:
>> In PVH dom0, it uses the linux local interrupt mechanism,
>> when it allocs irq for a gsi, it is dynamic, and follow
>> the principle of applying first, distributing first. And
>> the irq number is alloced from small to large, but the
>> applying gsi number is not, may gsi 38 comes before gsi 28,
>> it causes the irq number is not equal with the gsi number.
>> And when passthrough a device, QEMU will use device's gsi
>> number to do pirq mapping, but the gsi number is got from
>> file /sys/bus/pci/devices//irq, irq!= gsi, so it will
>> fail when mapping.
>> And in current linux codes, there is no method to get gsi
>> for userspace.
>>
>> For above purpose, record gsi of pcistub devices when init
>> pcistub and add a new syscall into privcmd to let userspace
>> can get gsi when they have a need.
>>
>> Co-developed-by: Huang Rui
>> Signed-off-by: Jiqian Chen
>> ---
>> drivers/xen/privcmd.c | 28 ++
>> drivers/xen/xen-pciback/pci_stub.c | 38 +++---
>> include/uapi/xen/privcmd.h | 7 ++
>> include/xen/acpi.h | 2 ++
>> 4 files changed, 72 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
>> index 67dfa4778864..5953a03b5cb0 100644
>> --- a/drivers/xen/privcmd.c
>> +++ b/drivers/xen/privcmd.c
>> @@ -45,6 +45,9 @@
>> #include
>> #include
>> #include
>> +#ifdef CONFIG_ACPI
>> +#include
>> +#endif
>>
>> #include "privcmd.h"
>>
>> @@ -842,6 +845,27 @@ static long privcmd_ioctl_mmap_resource(struct file
>> *file,
>> return rc;
>> }
>>
>> +static long privcmd_ioctl_gsi_from_dev(struct file *file, void __user
>> *udata)
>> +{
>> +struct privcmd_gsi_from_dev kdata;
>> +
>> +if (copy_from_user(, udata, sizeof(kdata)))
>> +return -EFAULT;
>> +
>> +#ifdef CONFIG_ACPI
>> +kdata.gsi = pcistub_get_gsi_from_sbdf(kdata.sbdf);
>> +if (kdata.gsi == -1)
>> +return -EINVAL;
>> +#else
>> +kdata.gsi = -1;
>
> Should we return an error instead, like -EINVAL, to make the behavior
> more similar to the CONFIG_ACPI case?
OK, will return -EINVAL if not config acpi.
Like:
static long privcmd_ioctl_gsi_from_dev(struct file *file, void __user *udata)
{
#ifdef CONFIG_ACPI
struct privcmd_gsi_from_dev kdata;
if (copy_from_user(, udata, sizeof(kdata)))
return -EFAULT;
kdata.gsi = pcistub_get_gsi_from_sbdf(kdata.sbdf);
if (kdata.gsi == -1)
return -EINVAL;
if (copy_to_user(udata, , sizeof(kdata)))
return -EFAULT;
return 0;
#else
return -EINVAL;
#endif
}
>
>
>> +#endif
>> +
>> +if (copy_to_user(udata, , sizeof(kdata)))
>> +return -EFAULT;
>> +
>> +return 0;
>> +}
>> +
>> #ifdef CONFIG_XEN_PRIVCMD_EVENTFD
>> /* Irqfd support */
>> static struct workqueue_struct *irqfd_cleanup_wq;
>> @@ -1529,6 +1553,10 @@ static long privcmd_ioctl(struct file *file,
>> ret = privcmd_ioctl_ioeventfd(file, udata);
>> break;
>>
>> +case IOCTL_PRIVCMD_GSI_FROM_DEV:
>> +ret = privcmd_ioctl_gsi_from_dev(file, udata);
>> +break;
>> +
>> default:
>> break;
>> }
>> diff --git a/drivers/xen/xen-pciback/pci_stub.c
>> b/drivers/xen/xen-pciback/pci_stub.c
>> index 2b90d832d0a7..4b62b4d377a9 100644
>> --- a/drivers/xen/xen-pciback/pci_stub.c
>> +++ b/drivers/xen/xen-pciback/pci_stub.c
>> @@ -56,6 +56,9 @@ struct pcistub_device {
>>
>> struct pci_dev *dev;
>> struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
>> +#ifdef CONFIG_ACPI
>> +int gsi;
>> +#endif
>> };
>>
>> /* Access to pcistub_devices & seized_devices lists and the
>> initialize_devices
>> @@ -88,6 +91,9 @@ static struct pcistub_device *pcistub_device_alloc(struct
>> pci_dev *dev)
>>
>> kref_init(>kref);
>> spin_lock_init(>lock);
>> +#ifdef CONFIG_ACPI
>> +psdev->gsi = -1;
>> +#endif
>>
>> return psdev;
>> }
>> @@ -220,6 +226,25 @@ static struct pci_dev
>> *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev,
>> return pci_dev;
>> }
>>
>> +#ifdef CONFIG_ACPI
>> +int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
>> +{
>> +struct pcistub_device *psdev;
>> +int domain = sbdf >> 16;
>> +int bus = (sbdf >> 8) & 0xff;
>> +int slot = (sbdf >> 3) & 0x1f;
>> +int func = sbdf & 0x7;
>
> you can use PCI_DEVFN PCI_SLOT PCI_FUNC pci_domain_nr instead of open
> coding.
Thanks, will change to use these in next version.
But pci_domain_nr requires passing in pci_dev.
Will change like:
int domain = (sbdf >> 16) & 0x;
int bus = PCI_BUS_NUM(sbdf);
int slot = PCI_SLOT(sbdf);
int func = PCI_FUNC(sbdf);
>
>
>> +
>> +psdev = pcistub_device_find(domain, bus, slot, func);
>> +
>> +if (!psdev)
>> +
Re: [RFC KERNEL PATCH v7 2/2] xen/privcmd: Add new syscall to get gsi from dev
On Wed, 15 May 2024, Jiqian Chen wrote:
> In PVH dom0, it uses the linux local interrupt mechanism,
> when it allocs irq for a gsi, it is dynamic, and follow
> the principle of applying first, distributing first. And
> the irq number is alloced from small to large, but the
> applying gsi number is not, may gsi 38 comes before gsi 28,
> it causes the irq number is not equal with the gsi number.
> And when passthrough a device, QEMU will use device's gsi
> number to do pirq mapping, but the gsi number is got from
> file /sys/bus/pci/devices//irq, irq!= gsi, so it will
> fail when mapping.
> And in current linux codes, there is no method to get gsi
> for userspace.
>
> For above purpose, record gsi of pcistub devices when init
> pcistub and add a new syscall into privcmd to let userspace
> can get gsi when they have a need.
>
> Co-developed-by: Huang Rui
> Signed-off-by: Jiqian Chen
> ---
> drivers/xen/privcmd.c | 28 ++
> drivers/xen/xen-pciback/pci_stub.c | 38 +++---
> include/uapi/xen/privcmd.h | 7 ++
> include/xen/acpi.h | 2 ++
> 4 files changed, 72 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
> index 67dfa4778864..5953a03b5cb0 100644
> --- a/drivers/xen/privcmd.c
> +++ b/drivers/xen/privcmd.c
> @@ -45,6 +45,9 @@
> #include
> #include
> #include
> +#ifdef CONFIG_ACPI
> +#include
> +#endif
>
> #include "privcmd.h"
>
> @@ -842,6 +845,27 @@ static long privcmd_ioctl_mmap_resource(struct file
> *file,
> return rc;
> }
>
> +static long privcmd_ioctl_gsi_from_dev(struct file *file, void __user *udata)
> +{
> + struct privcmd_gsi_from_dev kdata;
> +
> + if (copy_from_user(, udata, sizeof(kdata)))
> + return -EFAULT;
> +
> +#ifdef CONFIG_ACPI
> + kdata.gsi = pcistub_get_gsi_from_sbdf(kdata.sbdf);
> + if (kdata.gsi == -1)
> + return -EINVAL;
> +#else
> + kdata.gsi = -1;
Should we return an error instead, like -EINVAL, to make the behavior
more similar to the CONFIG_ACPI case?
> +#endif
> +
> + if (copy_to_user(udata, , sizeof(kdata)))
> + return -EFAULT;
> +
> + return 0;
> +}
> +
> #ifdef CONFIG_XEN_PRIVCMD_EVENTFD
> /* Irqfd support */
> static struct workqueue_struct *irqfd_cleanup_wq;
> @@ -1529,6 +1553,10 @@ static long privcmd_ioctl(struct file *file,
> ret = privcmd_ioctl_ioeventfd(file, udata);
> break;
>
> + case IOCTL_PRIVCMD_GSI_FROM_DEV:
> + ret = privcmd_ioctl_gsi_from_dev(file, udata);
> + break;
> +
> default:
> break;
> }
> diff --git a/drivers/xen/xen-pciback/pci_stub.c
> b/drivers/xen/xen-pciback/pci_stub.c
> index 2b90d832d0a7..4b62b4d377a9 100644
> --- a/drivers/xen/xen-pciback/pci_stub.c
> +++ b/drivers/xen/xen-pciback/pci_stub.c
> @@ -56,6 +56,9 @@ struct pcistub_device {
>
> struct pci_dev *dev;
> struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
> +#ifdef CONFIG_ACPI
> + int gsi;
> +#endif
> };
>
> /* Access to pcistub_devices & seized_devices lists and the
> initialize_devices
> @@ -88,6 +91,9 @@ static struct pcistub_device *pcistub_device_alloc(struct
> pci_dev *dev)
>
> kref_init(>kref);
> spin_lock_init(>lock);
> +#ifdef CONFIG_ACPI
> + psdev->gsi = -1;
> +#endif
>
> return psdev;
> }
> @@ -220,6 +226,25 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct
> xen_pcibk_device *pdev,
> return pci_dev;
> }
>
> +#ifdef CONFIG_ACPI
> +int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
> +{
> + struct pcistub_device *psdev;
> + int domain = sbdf >> 16;
> + int bus = (sbdf >> 8) & 0xff;
> + int slot = (sbdf >> 3) & 0x1f;
> + int func = sbdf & 0x7;
you can use PCI_DEVFN PCI_SLOT PCI_FUNC pci_domain_nr instead of open
coding.
> +
> + psdev = pcistub_device_find(domain, bus, slot, func);
> +
> + if (!psdev)
> + return -1;
> +
> + return psdev->gsi;
> +}
> +EXPORT_SYMBOL_GPL(pcistub_get_gsi_from_sbdf);
> +#endif
> +
> struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
> int domain, int bus,
> int slot, int func)
> @@ -367,14 +392,20 @@ static int pcistub_match(struct pci_dev *dev)
> return found;
> }
>
> -static int pcistub_init_device(struct pci_dev *dev)
> +static int pcistub_init_device(struct pcistub_device *psdev)
> {
> struct xen_pcibk_dev_data *dev_data;
> + struct pci_dev *dev;
> #ifdef CONFIG_ACPI
> int gsi, trigger, polarity;
> #endif
> int err = 0;
>
> + if (!psdev)
> + return -EINVAL;
> +
> + dev = psdev->dev;
> +
> dev_dbg(>dev, "initializing...\n");
>
> /* The PCI backend is not intended to be a module (or to work with
> @@ -448,6 +479,7 @@ static int
[RFC KERNEL PATCH v7 2/2] xen/privcmd: Add new syscall to get gsi from dev
In PVH dom0, it uses the linux local interrupt mechanism,
when it allocs irq for a gsi, it is dynamic, and follow
the principle of applying first, distributing first. And
the irq number is alloced from small to large, but the
applying gsi number is not, may gsi 38 comes before gsi 28,
it causes the irq number is not equal with the gsi number.
And when passthrough a device, QEMU will use device's gsi
number to do pirq mapping, but the gsi number is got from
file /sys/bus/pci/devices//irq, irq!= gsi, so it will
fail when mapping.
And in current linux codes, there is no method to get gsi
for userspace.
For above purpose, record gsi of pcistub devices when init
pcistub and add a new syscall into privcmd to let userspace
can get gsi when they have a need.
Co-developed-by: Huang Rui
Signed-off-by: Jiqian Chen
---
drivers/xen/privcmd.c | 28 ++
drivers/xen/xen-pciback/pci_stub.c | 38 +++---
include/uapi/xen/privcmd.h | 7 ++
include/xen/acpi.h | 2 ++
4 files changed, 72 insertions(+), 3 deletions(-)
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 67dfa4778864..5953a03b5cb0 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -45,6 +45,9 @@
#include
#include
#include
+#ifdef CONFIG_ACPI
+#include
+#endif
#include "privcmd.h"
@@ -842,6 +845,27 @@ static long privcmd_ioctl_mmap_resource(struct file *file,
return rc;
}
+static long privcmd_ioctl_gsi_from_dev(struct file *file, void __user *udata)
+{
+ struct privcmd_gsi_from_dev kdata;
+
+ if (copy_from_user(, udata, sizeof(kdata)))
+ return -EFAULT;
+
+#ifdef CONFIG_ACPI
+ kdata.gsi = pcistub_get_gsi_from_sbdf(kdata.sbdf);
+ if (kdata.gsi == -1)
+ return -EINVAL;
+#else
+ kdata.gsi = -1;
+#endif
+
+ if (copy_to_user(udata, , sizeof(kdata)))
+ return -EFAULT;
+
+ return 0;
+}
+
#ifdef CONFIG_XEN_PRIVCMD_EVENTFD
/* Irqfd support */
static struct workqueue_struct *irqfd_cleanup_wq;
@@ -1529,6 +1553,10 @@ static long privcmd_ioctl(struct file *file,
ret = privcmd_ioctl_ioeventfd(file, udata);
break;
+ case IOCTL_PRIVCMD_GSI_FROM_DEV:
+ ret = privcmd_ioctl_gsi_from_dev(file, udata);
+ break;
+
default:
break;
}
diff --git a/drivers/xen/xen-pciback/pci_stub.c
b/drivers/xen/xen-pciback/pci_stub.c
index 2b90d832d0a7..4b62b4d377a9 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -56,6 +56,9 @@ struct pcistub_device {
struct pci_dev *dev;
struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */
+#ifdef CONFIG_ACPI
+ int gsi;
+#endif
};
/* Access to pcistub_devices & seized_devices lists and the initialize_devices
@@ -88,6 +91,9 @@ static struct pcistub_device *pcistub_device_alloc(struct
pci_dev *dev)
kref_init(>kref);
spin_lock_init(>lock);
+#ifdef CONFIG_ACPI
+ psdev->gsi = -1;
+#endif
return psdev;
}
@@ -220,6 +226,25 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct
xen_pcibk_device *pdev,
return pci_dev;
}
+#ifdef CONFIG_ACPI
+int pcistub_get_gsi_from_sbdf(unsigned int sbdf)
+{
+ struct pcistub_device *psdev;
+ int domain = sbdf >> 16;
+ int bus = (sbdf >> 8) & 0xff;
+ int slot = (sbdf >> 3) & 0x1f;
+ int func = sbdf & 0x7;
+
+ psdev = pcistub_device_find(domain, bus, slot, func);
+
+ if (!psdev)
+ return -1;
+
+ return psdev->gsi;
+}
+EXPORT_SYMBOL_GPL(pcistub_get_gsi_from_sbdf);
+#endif
+
struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev,
int domain, int bus,
int slot, int func)
@@ -367,14 +392,20 @@ static int pcistub_match(struct pci_dev *dev)
return found;
}
-static int pcistub_init_device(struct pci_dev *dev)
+static int pcistub_init_device(struct pcistub_device *psdev)
{
struct xen_pcibk_dev_data *dev_data;
+ struct pci_dev *dev;
#ifdef CONFIG_ACPI
int gsi, trigger, polarity;
#endif
int err = 0;
+ if (!psdev)
+ return -EINVAL;
+
+ dev = psdev->dev;
+
dev_dbg(>dev, "initializing...\n");
/* The PCI backend is not intended to be a module (or to work with
@@ -448,6 +479,7 @@ static int pcistub_init_device(struct pci_dev *dev)
dev_err(>dev, "Fail to get gsi info!\n");
goto config_release;
}
+ psdev->gsi = gsi;
if (xen_initial_domain() && xen_pvh_domain()) {
err = xen_pvh_setup_gsi(gsi, trigger, polarity);
@@ -495,7 +527,7 @@ static int __init pcistub_init_devices_late(void)
spin_unlock_irqrestore(_devices_lock, flags);
- err =
