From: Shenming Lu <lushenming@huawei.com>
To: Alex Williamson <alex.williamson@redhat.com>,
Cornelia Huck <cohuck@redhat.com>, Will Deacon <will@kernel.org>,
Robin Murphy <robin.murphy@arm.com>,
Joerg Roedel <joro@8bytes.org>,
Jean-Philippe Brucker <jean-philippe@linaro.org>,
Eric Auger <eric.auger@redhat.com>, <kvm@vger.kernel.org>,
<linux-kernel@vger.kernel.org>,
<linux-arm-kernel@lists.infradead.org>,
<iommu@lists.linux-foundation.org>, <linux-api@vger.kernel.org>
Cc: Kevin Tian <kevin.tian@intel.com>,
Lu Baolu <baolu.lu@linux.intel.com>, <yi.l.liu@intel.com>,
Christoph Hellwig <hch@infradead.org>,
Jonathan Cameron <Jonathan.Cameron@huawei.com>,
Barry Song <song.bao.hua@hisilicon.com>,
<wanghaibin.wang@huawei.com>, <yuzenghui@huawei.com>,
<lushenming@huawei.com>
Subject: [RFC PATCH v3 8/8] vfio: Add nested IOPF support
Date: Fri, 9 Apr 2021 11:44:20 +0800 [thread overview]
Message-ID: <20210409034420.1799-9-lushenming@huawei.com> (raw)
In-Reply-To: <20210409034420.1799-1-lushenming@huawei.com>
To set up nested mode, drivers such as vfio_pci need to register a
handler to receive stage/level 1 faults from the IOMMU, but since
currently each device can only have one iommu dev fault handler,
and if stage 2 IOPF is already enabled (VFIO_IOMMU_ENABLE_IOPF),
we choose to update the registered handler (a consolidated one) via
flags (set FAULT_REPORT_NESTED_L1), and further deliver the received
stage 1 faults in the handler to the guest through a newly added
vfio_device_ops callback.
Signed-off-by: Shenming Lu <lushenming@huawei.com>
---
drivers/vfio/vfio.c | 81 +++++++++++++++++++++++++++++++++
drivers/vfio/vfio_iommu_type1.c | 49 +++++++++++++++++++-
include/linux/vfio.h | 12 +++++
3 files changed, 141 insertions(+), 1 deletion(-)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 44c8dfabf7de..4245f15914bf 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -2356,6 +2356,87 @@ struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
}
EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);
+/*
+ * Register/Update the VFIO IOPF handler to receive
+ * nested stage/level 1 faults.
+ */
+int vfio_iommu_dev_fault_handler_register_nested(struct device *dev)
+{
+ struct vfio_container *container;
+ struct vfio_group *group;
+ struct vfio_iommu_driver *driver;
+ int ret;
+
+ if (!dev)
+ return -EINVAL;
+
+ group = vfio_group_get_from_dev(dev);
+ if (!group)
+ return -ENODEV;
+
+ ret = vfio_group_add_container_user(group);
+ if (ret)
+ goto out;
+
+ container = group->container;
+ driver = container->iommu_driver;
+ if (likely(driver && driver->ops->register_handler))
+ ret = driver->ops->register_handler(container->iommu_data, dev);
+ else
+ ret = -ENOTTY;
+
+ vfio_group_try_dissolve_container(group);
+
+out:
+ vfio_group_put(group);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_iommu_dev_fault_handler_register_nested);
+
+int vfio_iommu_dev_fault_handler_unregister_nested(struct device *dev)
+{
+ struct vfio_container *container;
+ struct vfio_group *group;
+ struct vfio_iommu_driver *driver;
+ int ret;
+
+ if (!dev)
+ return -EINVAL;
+
+ group = vfio_group_get_from_dev(dev);
+ if (!group)
+ return -ENODEV;
+
+ ret = vfio_group_add_container_user(group);
+ if (ret)
+ goto out;
+
+ container = group->container;
+ driver = container->iommu_driver;
+ if (likely(driver && driver->ops->unregister_handler))
+ ret = driver->ops->unregister_handler(container->iommu_data, dev);
+ else
+ ret = -ENOTTY;
+
+ vfio_group_try_dissolve_container(group);
+
+out:
+ vfio_group_put(group);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_iommu_dev_fault_handler_unregister_nested);
+
+int vfio_transfer_iommu_fault(struct device *dev, struct iommu_fault *fault)
+{
+ struct vfio_device *device = dev_get_drvdata(dev);
+
+ if (unlikely(!device->ops->transfer))
+ return -EOPNOTSUPP;
+
+ return device->ops->transfer(device->device_data, fault);
+}
+EXPORT_SYMBOL_GPL(vfio_transfer_iommu_fault);
+
/**
* Module/class support
*/
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index ba2b5a1cf6e9..9d1adeddb303 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -3821,13 +3821,32 @@ static int vfio_iommu_type1_dma_map_iopf(struct iommu_fault *fault, void *data)
struct vfio_batch batch;
struct vfio_range *range;
dma_addr_t iova = ALIGN_DOWN(fault->prm.addr, PAGE_SIZE);
- int access_flags = 0;
+ int access_flags = 0, nested;
size_t premap_len, map_len, mapped_len = 0;
unsigned long bit_offset, vaddr, pfn, i, npages;
int ret;
enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
struct iommu_page_response resp = {0};
+ if (vfio_dev_domian_nested(dev, &nested))
+ return -ENODEV;
+
+ /*
+ * When configured in nested mode, further deliver the
+ * stage/level 1 faults to the guest.
+ */
+ if (nested) {
+ bool l2;
+
+ if (fault->type == IOMMU_FAULT_PAGE_REQ)
+ l2 = fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_L2;
+ if (fault->type == IOMMU_FAULT_DMA_UNRECOV)
+ l2 = fault->event.flags & IOMMU_FAULT_UNRECOV_L2;
+
+ if (!l2)
+ return vfio_transfer_iommu_fault(dev, fault);
+ }
+
if (fault->type != IOMMU_FAULT_PAGE_REQ)
return -EOPNOTSUPP;
@@ -4201,6 +4220,32 @@ static void vfio_iommu_type1_notify(void *iommu_data,
wake_up_all(&iommu->vaddr_wait);
}
+static int vfio_iommu_type1_register_handler(void *iommu_data,
+ struct device *dev)
+{
+ struct vfio_iommu *iommu = iommu_data;
+
+ if (iommu->iopf_enabled)
+ return iommu_update_device_fault_handler(dev, ~0,
+ FAULT_REPORT_NESTED_L1);
+ else
+ return iommu_register_device_fault_handler(dev,
+ vfio_iommu_type1_dma_map_iopf,
+ FAULT_REPORT_NESTED_L1, dev);
+}
+
+static int vfio_iommu_type1_unregister_handler(void *iommu_data,
+ struct device *dev)
+{
+ struct vfio_iommu *iommu = iommu_data;
+
+ if (iommu->iopf_enabled)
+ return iommu_update_device_fault_handler(dev,
+ ~FAULT_REPORT_NESTED_L1, 0);
+ else
+ return iommu_unregister_device_fault_handler(dev);
+}
+
static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
.name = "vfio-iommu-type1",
.owner = THIS_MODULE,
@@ -4216,6 +4261,8 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
.dma_rw = vfio_iommu_type1_dma_rw,
.group_iommu_domain = vfio_iommu_type1_group_iommu_domain,
.notify = vfio_iommu_type1_notify,
+ .register_handler = vfio_iommu_type1_register_handler,
+ .unregister_handler = vfio_iommu_type1_unregister_handler,
};
static int __init vfio_iommu_type1_init(void)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index a7b426d579df..4621d8f0395d 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -29,6 +29,8 @@
* @match: Optional device name match callback (return: 0 for no-match, >0 for
* match, -errno for abort (ex. match with insufficient or incorrect
* additional args)
+ * @transfer: Optional. Transfer the received stage/level 1 faults to the guest
+ * for nested mode.
*/
struct vfio_device_ops {
char *name;
@@ -43,6 +45,7 @@ struct vfio_device_ops {
int (*mmap)(void *device_data, struct vm_area_struct *vma);
void (*request)(void *device_data, unsigned int count);
int (*match)(void *device_data, char *buf);
+ int (*transfer)(void *device_data, struct iommu_fault *fault);
};
extern struct iommu_group *vfio_iommu_group_get(struct device *dev);
@@ -100,6 +103,10 @@ struct vfio_iommu_driver_ops {
struct iommu_group *group);
void (*notify)(void *iommu_data,
enum vfio_iommu_notify_type event);
+ int (*register_handler)(void *iommu_data,
+ struct device *dev);
+ int (*unregister_handler)(void *iommu_data,
+ struct device *dev);
};
extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -161,6 +168,11 @@ extern int vfio_unregister_notifier(struct device *dev,
struct kvm;
extern void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm);
+extern int vfio_iommu_dev_fault_handler_register_nested(struct device *dev);
+extern int vfio_iommu_dev_fault_handler_unregister_nested(struct device *dev);
+extern int vfio_transfer_iommu_fault(struct device *dev,
+ struct iommu_fault *fault);
+
/*
* Sub-module helpers
*/
--
2.19.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2021-04-09 3:48 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-09 3:44 [RFC PATCH v3 0/8] Add IOPF support for VFIO passthrough Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 1/8] iommu: Evolve the device fault reporting framework Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:37 ` Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 2/8] vfio/type1: Add a page fault handler Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:38 ` Shenming Lu
2021-05-24 22:11 ` Alex Williamson
2021-05-27 11:16 ` Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 3/8] vfio/type1: Add an MMU notifier to avoid pinning Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:37 ` Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 4/8] vfio/type1: Pre-map more pages than requested in the IOPF handling Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:37 ` Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 5/8] vfio/type1: VFIO_IOMMU_ENABLE_IOPF Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:38 ` Shenming Lu
2021-05-24 22:11 ` Alex Williamson
2021-05-27 11:15 ` Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 6/8] vfio/type1: No need to statically pin and map if IOPF enabled Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:39 ` Shenming Lu
2021-04-09 3:44 ` [RFC PATCH v3 7/8] vfio/type1: Add selective DMA faulting support Shenming Lu
2021-05-18 18:58 ` Alex Williamson
2021-05-21 6:39 ` Shenming Lu
2021-04-09 3:44 ` Shenming Lu [this message]
2021-05-18 18:58 ` [RFC PATCH v3 8/8] vfio: Add nested IOPF support Alex Williamson
2021-05-21 7:59 ` Shenming Lu
2021-05-24 13:11 ` Shenming Lu
2021-05-24 22:11 ` Alex Williamson
2021-05-27 11:03 ` Shenming Lu
2021-05-27 11:18 ` Lu Baolu
2021-06-01 4:36 ` Shenming Lu
2021-04-26 1:41 ` [RFC PATCH v3 0/8] Add IOPF support for VFIO passthrough Shenming Lu
2021-05-11 11:30 ` Shenming Lu
2021-05-18 18:57 ` Alex Williamson
2021-05-21 6:37 ` Shenming Lu
2021-05-24 22:11 ` Alex Williamson
2021-05-27 11:25 ` Shenming Lu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210409034420.1799-9-lushenming@huawei.com \
--to=lushenming@huawei.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=alex.williamson@redhat.com \
--cc=baolu.lu@linux.intel.com \
--cc=cohuck@redhat.com \
--cc=eric.auger@redhat.com \
--cc=hch@infradead.org \
--cc=iommu@lists.linux-foundation.org \
--cc=jean-philippe@linaro.org \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=song.bao.hua@hisilicon.com \
--cc=wanghaibin.wang@huawei.com \
--cc=will@kernel.org \
--cc=yi.l.liu@intel.com \
--cc=yuzenghui@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).