Interrupt context is statically allocated at the time interrupts
are allocated. Following allocation, the context is managed by
directly accessing the elements of the array using the vector
as index. The storage is released when interrupts are disabled.
It is possible to dynamically allocate a single MSI-X index
after MSI-X has been enabled. A dynamic storage for interrupt context
is needed to support this. Replace the interrupt context array with an
xarray (similar to what the core uses as store for MSI descriptors)
that can support the dynamic expansion while maintaining the
custom that uses the vector as index.
Use the new data storage to allocate all elements once and free all
elements together. Dynamic usage follows.
Create helpers with understanding that it is only possible
to (after initial MSI-X enabling) allocate a single MSI-X index at
a time. The only time multiple MSI-X are allocated is during initial
MSI-X enabling where failure results in no allocations.
Signed-off-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>
---
Changes since RFC V1:
- Let vfio_irq_ctx_alloc_single() return pointer to allocated
context. (Alex)
- Transition INTx allocation to simplified vfio_irq_ctx_alloc_single().
- Improve accuracy of changelog.
drivers/vfio/pci/vfio_pci_core.c | 1 +
drivers/vfio/pci/vfio_pci_intrs.c | 77 ++++++++++++++++++++-----------
include/linux/vfio_pci_core.h | 2 +-
3 files changed, 53 insertions(+), 27 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index a5ab416cf476..ae0e161c7fc9 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -2102,6 +2102,7 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev)
INIT_LIST_HEAD(&vdev->vma_list);
INIT_LIST_HEAD(&vdev->sriov_pfs_item);
init_rwsem(&vdev->memory_lock);
+ xa_init(&vdev->ctx);
return 0;
}
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index ece371ebea00..00119641aa19 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -52,25 +52,60 @@ static
struct vfio_pci_irq_ctx *vfio_irq_ctx_get(struct vfio_pci_core_device *vdev,
unsigned long index)
{
- if (index >= vdev->num_ctx)
- return NULL;
- return &vdev->ctx[index];
+ return xa_load(&vdev->ctx, index);
}
static void vfio_irq_ctx_free_all(struct vfio_pci_core_device *vdev)
{
- kfree(vdev->ctx);
+ struct vfio_pci_irq_ctx *ctx;
+ unsigned long index;
+
+ xa_for_each(&vdev->ctx, index, ctx) {
+ xa_erase(&vdev->ctx, index);
+ kfree(ctx);
+ }
+}
+
+static struct vfio_pci_irq_ctx *
+vfio_irq_ctx_alloc_single(struct vfio_pci_core_device *vdev,
+ unsigned long index)
+{
+ struct vfio_pci_irq_ctx *ctx;
+ int ret;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
+ if (!ctx)
+ return NULL;
+
+ ret = xa_insert(&vdev->ctx, index, ctx, GFP_KERNEL_ACCOUNT);
+ if (ret) {
+ kfree(ctx);
+ return NULL;
+ }
+
+ return ctx;
}
+/* Only called during initial interrupt enabling. Never after. */
static int vfio_irq_ctx_alloc_num(struct vfio_pci_core_device *vdev,
unsigned long num)
{
- vdev->ctx = kcalloc(num, sizeof(struct vfio_pci_irq_ctx),
- GFP_KERNEL_ACCOUNT);
- if (!vdev->ctx)
- return -ENOMEM;
+ struct vfio_pci_irq_ctx *ctx;
+ unsigned long index;
+
+ WARN_ON(!xa_empty(&vdev->ctx));
+
+ for (index = 0; index < num; index++) {
+ ctx = vfio_irq_ctx_alloc_single(vdev, index);
+ if (!ctx)
+ goto err;
+ }
return 0;
+
+err:
+ vfio_irq_ctx_free_all(vdev);
+ return -ENOMEM;
}
/*
@@ -218,7 +253,6 @@ static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
static int vfio_intx_enable(struct vfio_pci_core_device *vdev)
{
struct vfio_pci_irq_ctx *ctx;
- int ret;
if (!is_irq_none(vdev))
return -EINVAL;
@@ -226,15 +260,9 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev)
if (!vdev->pdev->irq)
return -ENODEV;
- ret = vfio_irq_ctx_alloc_num(vdev, 1);
- if (ret)
- return ret;
-
- ctx = vfio_irq_ctx_get(vdev, 0);
- if (!ctx) {
- vfio_irq_ctx_free_all(vdev);
- return -EINVAL;
- }
+ ctx = vfio_irq_ctx_alloc_single(vdev, 0);
+ if (!ctx)
+ return -ENOMEM;
vdev->num_ctx = 1;
@@ -486,16 +514,13 @@ static void vfio_msi_disable(struct vfio_pci_core_device *vdev, bool msix)
{
struct pci_dev *pdev = vdev->pdev;
struct vfio_pci_irq_ctx *ctx;
- unsigned int i;
+ unsigned long i;
u16 cmd;
- for (i = 0; i < vdev->num_ctx; i++) {
- ctx = vfio_irq_ctx_get(vdev, i);
- if (ctx) {
- vfio_virqfd_disable(&ctx->unmask);
- vfio_virqfd_disable(&ctx->mask);
- vfio_msi_set_vector_signal(vdev, i, -1, msix);
- }
+ xa_for_each(&vdev->ctx, i, ctx) {
+ vfio_virqfd_disable(&ctx->unmask);
+ vfio_virqfd_disable(&ctx->mask);
+ vfio_msi_set_vector_signal(vdev, i, -1, msix);
}
cmd = vfio_pci_memory_lock_and_enable(vdev);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index 367fd79226a3..61d7873a3973 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -59,7 +59,7 @@ struct vfio_pci_core_device {
struct perm_bits *msi_perm;
spinlock_t irqlock;
struct mutex igate;
- struct vfio_pci_irq_ctx *ctx;
+ struct xarray ctx;
int num_ctx;
int irq_type;
int num_regions;
--
2.34.1
