The usual way to configure a device interrupt from userland is to write
the /proc/irq/<irq>/smp_affinity or smp_affinity_list files. When using
vfio to implement a device driver or a virtual machine monitor, this may
not be ideal: the process managing the vfio device interrupts may not be
granted root privilege, for security reasons. Thus it cannot directly
control the interrupt affinity and has to rely on an external command.
This patch extends the VFIO_DEVICE_SET_IRQS ioctl() with a new data flag
to specify the affinity of interrupts of a vfio pci device.
The CPU affinity mask argument must be a subset of the process cpuset,
otherwise an error -EPERM is returned.
The vfio_irq_set argument shall be set-up in the following way:
- the 'flags' field have the new flag VFIO_IRQ_SET_DATA_CPUSET set
as well as VFIO_IRQ_SET_ACTION_TRIGGER.
- the variable-length 'data' field is a cpu_set_t structure, as
for the sched_setaffinity() syscall, the size of which is derived
from 'argsz'.
Signed-off-by: Fred Griffoul <fgriffo@xxxxxxxxxxxx>
---
drivers/vfio/pci/vfio_pci_core.c | 2 +-
drivers/vfio/pci/vfio_pci_intrs.c | 41 +++++++++++++++++++++++++++++++
drivers/vfio/vfio_main.c | 15 ++++++++---
include/uapi/linux/vfio.h | 15 ++++++++++-
4 files changed, 67 insertions(+), 6 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 80cae87fff36..fbc490703031 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1174,7 +1174,7 @@ static int vfio_pci_ioctl_get_irq_info(struct vfio_pci_core_device *vdev,
return -EINVAL;
}
- info.flags = VFIO_IRQ_INFO_EVENTFD;
+ info.flags = VFIO_IRQ_INFO_EVENTFD | VFIO_IRQ_INFO_CPUSET;
info.count = vfio_pci_get_irq_count(vdev, info.index);
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 8382c5834335..b339c42cb1c0 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -19,6 +19,7 @@
#include <linux/vfio.h>
#include <linux/wait.h>
#include <linux/slab.h>
+#include <linux/cpuset.h>
#include "vfio_pci_priv.h"
@@ -82,6 +83,40 @@ vfio_irq_ctx_alloc(struct vfio_pci_core_device *vdev, unsigned long index)
return ctx;
}
+static int vfio_pci_set_affinity(struct vfio_pci_core_device *vdev,
+ unsigned int start, unsigned int count,
+ struct cpumask *irq_mask)
+{
+ cpumask_var_t allowed_mask;
+ int irq, err = 0;
+ unsigned int i;
+
+ if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
+ return -ENOMEM;
+
+ cpuset_cpus_allowed(current, allowed_mask);
+ if (!cpumask_subset(irq_mask, allowed_mask)) {
+ err = -EPERM;
+ goto finish;
+ }
+
+ for (i = start; i < start + count; i++) {
+ irq = pci_irq_vector(vdev->pdev, i);
+ if (irq < 0) {
+ err = -EINVAL;
+ break;
+ }
+
+ err = irq_set_affinity(irq, irq_mask);
+ if (err)
+ break;
+ }
+
+finish:
+ free_cpumask_var(allowed_mask);
+ return err;
+}
+
/*
* INTx
*/
@@ -665,6 +700,9 @@ static int vfio_pci_set_intx_trigger(struct vfio_pci_core_device *vdev,
if (!is_intx(vdev))
return -EINVAL;
+ if (flags & VFIO_IRQ_SET_DATA_CPUSET)
+ return vfio_pci_set_affinity(vdev, start, count, data);
+
if (flags & VFIO_IRQ_SET_DATA_NONE) {
vfio_send_intx_eventfd(vdev, vfio_irq_ctx_get(vdev, 0));
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
@@ -713,6 +751,9 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev,
if (!irq_is(vdev, index))
return -EINVAL;
+ if (flags & VFIO_IRQ_SET_DATA_CPUSET)
+ return vfio_pci_set_affinity(vdev, start, count, data);
+
for (i = start; i < start + count; i++) {
ctx = vfio_irq_ctx_get(vdev, i);
if (!ctx)
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index e97d796a54fb..2e4f4e37cf89 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -1505,23 +1505,30 @@ int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,
size = 0;
break;
case VFIO_IRQ_SET_DATA_BOOL:
- size = sizeof(uint8_t);
+ size = size_mul(hdr->count, sizeof(uint8_t));
break;
case VFIO_IRQ_SET_DATA_EVENTFD:
- size = sizeof(int32_t);
+ size = size_mul(hdr->count, sizeof(int32_t));
+ break;
+ case VFIO_IRQ_SET_DATA_CPUSET:
+ size = hdr->argsz - minsz;
+ if (size < cpumask_size())
+ return -EINVAL;
+ if (size > cpumask_size())
+ size = cpumask_size();
break;
default:
return -EINVAL;
}
if (size) {
- if (hdr->argsz - minsz < hdr->count * size)
+ if (hdr->argsz - minsz < size)
return -EINVAL;
if (!data_size)
return -EINVAL;
- *data_size = hdr->count * size;
+ *data_size = size;
}
return 0;
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 2b68e6cdf190..d2edf6b725f8 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -530,6 +530,10 @@ struct vfio_region_info_cap_nvlink2_lnkspd {
* Absence of the NORESIZE flag indicates that vectors can be enabled
* and disabled dynamically without impacting other vectors within the
* index.
+ *
+ * The CPUSET flag indicates the interrupt index supports setting
+ * its affinity with a cpu_set_t configured with the SET_IRQ
+ * ioctl().
*/
struct vfio_irq_info {
__u32 argsz;
@@ -538,6 +542,7 @@ struct vfio_irq_info {
#define VFIO_IRQ_INFO_MASKABLE (1 << 1)
#define VFIO_IRQ_INFO_AUTOMASKED (1 << 2)
#define VFIO_IRQ_INFO_NORESIZE (1 << 3)
+#define VFIO_IRQ_INFO_CPUSET (1 << 4)
__u32 index; /* IRQ index */
__u32 count; /* Number of IRQs within this index */
};
@@ -580,6 +585,12 @@ struct vfio_irq_info {
*
* Note that ACTION_[UN]MASK specify user->kernel signaling (irqfds) while
* ACTION_TRIGGER specifies kernel->user signaling.
+ *
+ * DATA_CPUSET specifies the affinity for the range of interrupt vectors.
+ * It must be set with ACTION_TRIGGER in 'flags'. The variable-length 'data'
+ * array is the CPU affinity mask represented as a 'cpu_set_t' structure, as
+ * for the sched_setaffinity() syscall argument: the 'argsz' field is used
+ * to check the actual cpu_set_t size.
*/
struct vfio_irq_set {
__u32 argsz;
@@ -587,6 +598,7 @@ struct vfio_irq_set {
#define VFIO_IRQ_SET_DATA_NONE (1 << 0) /* Data not present */
#define VFIO_IRQ_SET_DATA_BOOL (1 << 1) /* Data is bool (u8) */
#define VFIO_IRQ_SET_DATA_EVENTFD (1 << 2) /* Data is eventfd (s32) */
+#define VFIO_IRQ_SET_DATA_CPUSET (1 << 6) /* Data is cpu_set_t */
#define VFIO_IRQ_SET_ACTION_MASK (1 << 3) /* Mask interrupt */
#define VFIO_IRQ_SET_ACTION_UNMASK (1 << 4) /* Unmask interrupt */
#define VFIO_IRQ_SET_ACTION_TRIGGER (1 << 5) /* Trigger interrupt */
@@ -599,7 +611,8 @@ struct vfio_irq_set {
#define VFIO_IRQ_SET_DATA_TYPE_MASK (VFIO_IRQ_SET_DATA_NONE | \
VFIO_IRQ_SET_DATA_BOOL | \
- VFIO_IRQ_SET_DATA_EVENTFD)
+ VFIO_IRQ_SET_DATA_EVENTFD | \
+ VFIO_IRQ_SET_DATA_CPUSET)
#define VFIO_IRQ_SET_ACTION_TYPE_MASK (VFIO_IRQ_SET_ACTION_MASK | \
VFIO_IRQ_SET_ACTION_UNMASK | \
VFIO_IRQ_SET_ACTION_TRIGGER)
--
2.40.1
