summaryrefslogtreecommitdiff
path: root/drivers/vfio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio')
-rw-r--r--drivers/vfio/pci/vfio_pci.c48
-rw-r--r--drivers/vfio/pci/vfio_pci_config.c31
-rw-r--r--drivers/vfio/pci/vfio_pci_intrs.c2
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c10
-rw-r--r--drivers/vfio/vfio_iommu_type1.c14
5 files changed, 83 insertions, 22 deletions
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 7338e43faa17..c94167d87178 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -356,11 +356,20 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
/*
- * Try to reset the device. The success of this is dependent on
- * being able to lock the device, which is not always possible.
+ * Try to get the locks ourselves to prevent a deadlock. The
+ * success of this is dependent on being able to lock the device,
+ * which is not always possible.
+ * We can not use the "try" reset interface here, which will
+ * overwrite the previously restored configuration information.
*/
- if (vdev->reset_works && !pci_try_reset_function(pdev))
- vdev->needs_reset = false;
+ if (vdev->reset_works && pci_cfg_access_trylock(pdev)) {
+ if (device_trylock(&pdev->dev)) {
+ if (!__pci_reset_function_locked(pdev))
+ vdev->needs_reset = false;
+ device_unlock(&pdev->dev);
+ }
+ pci_cfg_access_unlock(pdev);
+ }
pci_restore_state(pdev);
out:
@@ -417,10 +426,14 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
{
if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) {
u8 pin;
+
+ if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) ||
+ vdev->nointx || vdev->pdev->is_virtfn)
+ return 0;
+
pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin);
- if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && !vdev->nointx && pin)
- return 1;
+ return pin ? 1 : 0;
} else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) {
u8 pos;
u16 flags;
@@ -716,6 +729,7 @@ static long vfio_pci_ioctl(void *device_data,
{
void __iomem *io;
size_t size;
+ u16 orig_cmd;
info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
info.flags = 0;
@@ -731,15 +745,23 @@ static long vfio_pci_ioctl(void *device_data,
break;
}
- /* Is it really there? */
+ /*
+ * Is it really there? Enable memory decode for
+ * implicit access in pci_map_rom().
+ */
+ pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
+ pci_write_config_word(pdev, PCI_COMMAND,
+ orig_cmd | PCI_COMMAND_MEMORY);
+
io = pci_map_rom(pdev, &size);
- if (!io || !size) {
+ if (io) {
+ info.flags = VFIO_REGION_INFO_FLAG_READ;
+ pci_unmap_rom(pdev, io);
+ } else {
info.size = 0;
- break;
}
- pci_unmap_rom(pdev, io);
- info.flags = VFIO_REGION_INFO_FLAG_READ;
+ pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
break;
}
case VFIO_PCI_VGA_REGION_INDEX:
@@ -1467,11 +1489,11 @@ static void __init vfio_pci_fill_ids(void)
rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
subvendor, subdevice, class, class_mask, 0);
if (rc)
- pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+ pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
vendor, device, subvendor, subdevice,
class, class_mask, rc);
else
- pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+ pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
vendor, device, subvendor, subdevice,
class, class_mask);
}
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 7b8a957b008d..84905d074c4f 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1182,8 +1182,10 @@ static int vfio_msi_cap_len(struct vfio_pci_device *vdev, u8 pos)
return -ENOMEM;
ret = init_pci_cap_msi_perm(vdev->msi_perm, len, flags);
- if (ret)
+ if (ret) {
+ kfree(vdev->msi_perm);
return ret;
+ }
return len;
}
@@ -1607,6 +1609,15 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
}
/*
+ * Nag about hardware bugs, hopefully to have vendors fix them, but at least
+ * to collect a list of dependencies for the VF INTx pin quirk below.
+ */
+static const struct pci_device_id known_bogus_vf_intx_pin[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x270c) },
+ {}
+};
+
+/*
* For each device we allocate a pci_config_map that indicates the
* capability occupying each dword and thus the struct perm_bits we
* use for read and write. We also allocate a virtualized config
@@ -1671,6 +1682,24 @@ int vfio_config_init(struct vfio_pci_device *vdev)
if (pdev->is_virtfn) {
*(__le16 *)&vconfig[PCI_VENDOR_ID] = cpu_to_le16(pdev->vendor);
*(__le16 *)&vconfig[PCI_DEVICE_ID] = cpu_to_le16(pdev->device);
+
+ /*
+ * Per SR-IOV spec rev 1.1, 3.4.1.18 the interrupt pin register
+ * does not apply to VFs and VFs must implement this register
+ * as read-only with value zero. Userspace is not readily able
+ * to identify whether a device is a VF and thus that the pin
+ * definition on the device is bogus should it violate this
+ * requirement. We already virtualize the pin register for
+ * other purposes, so we simply need to replace the bogus value
+ * and consider VFs when we determine INTx IRQ count.
+ */
+ if (vconfig[PCI_INTERRUPT_PIN] &&
+ !pci_match_id(known_bogus_vf_intx_pin, pdev))
+ pci_warn(pdev,
+ "Hardware bug: VF reports bogus INTx pin %d\n",
+ vconfig[PCI_INTERRUPT_PIN]);
+
+ vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */
}
if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx)
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 1c46045b0e7f..94594dc63c41 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -297,8 +297,8 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev,
irq = pci_irq_vector(pdev, vector);
if (vdev->ctx[vector].trigger) {
- free_irq(irq, vdev->ctx[vector].trigger);
irq_bypass_unregister_producer(&vdev->ctx[vector].producer);
+ free_irq(irq, vdev->ctx[vector].trigger);
kfree(vdev->ctx[vector].name);
eventfd_ctx_put(vdev->ctx[vector].trigger);
vdev->ctx[vector].trigger = NULL;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 70c748a5fbcc..a8e25f9409fa 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -406,6 +406,7 @@ static void tce_iommu_release(void *iommu_data)
{
struct tce_container *container = iommu_data;
struct tce_iommu_group *tcegrp;
+ struct tce_iommu_prereg *tcemem, *tmtmp;
long i;
while (tce_groups_attached(container)) {
@@ -428,13 +429,8 @@ static void tce_iommu_release(void *iommu_data)
tce_iommu_free_table(container, tbl);
}
- while (!list_empty(&container->prereg_list)) {
- struct tce_iommu_prereg *tcemem;
-
- tcemem = list_first_entry(&container->prereg_list,
- struct tce_iommu_prereg, next);
- WARN_ON_ONCE(tce_iommu_prereg_free(container, tcemem));
- }
+ list_for_each_entry_safe(tcemem, tmtmp, &container->prereg_list, next)
+ WARN_ON(tce_iommu_prereg_free(container, tcemem));
tce_iommu_disable(container);
if (container->mm)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 1d48e62f4f52..0d5b667c0e65 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -53,10 +53,16 @@ module_param_named(disable_hugepages,
MODULE_PARM_DESC(disable_hugepages,
"Disable VFIO IOMMU support for IOMMU hugepages.");
+static unsigned int dma_entry_limit __read_mostly = U16_MAX;
+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644);
+MODULE_PARM_DESC(dma_entry_limit,
+ "Maximum number of user DMA mappings per container (65535).");
+
struct vfio_iommu {
struct list_head domain_list;
struct mutex lock;
struct rb_root dma_list;
+ unsigned int dma_avail;
bool v2;
bool nesting;
};
@@ -384,6 +390,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
vfio_unmap_unpin(iommu, dma);
vfio_unlink_dma(iommu, dma);
kfree(dma);
+ iommu->dma_avail++;
}
static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
@@ -584,12 +591,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
return -EEXIST;
}
+ if (!iommu->dma_avail) {
+ mutex_unlock(&iommu->lock);
+ return -ENOSPC;
+ }
+
dma = kzalloc(sizeof(*dma), GFP_KERNEL);
if (!dma) {
mutex_unlock(&iommu->lock);
return -ENOMEM;
}
+ iommu->dma_avail--;
dma->iova = iova;
dma->vaddr = vaddr;
dma->prot = prot;
@@ -905,6 +918,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
INIT_LIST_HEAD(&iommu->domain_list);
iommu->dma_list = RB_ROOT;
+ iommu->dma_avail = dma_entry_limit;
mutex_init(&iommu->lock);
return iommu;
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-25 23:42:31 +0000