From: Eric Auger <eric.auger@redhat.com>
To: eric.auger.pro@gmail.com, eric.auger@redhat.com,
iommu@lists.linux-foundation.org, linux-kernel@vger.kernel.org,
kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu,
will@kernel.org, maz@kernel.org, robin.murphy@arm.com,
joro@8bytes.org, alex.williamson@redhat.com, tn@semihalf.com,
zhukeqian1@huawei.com
Cc: jean-philippe@linaro.org, wangxingang5@huawei.com,
lushenming@huawei.com, vivek.gautam@arm.com, vsethi@nvidia.com,
zhangfei.gao@linaro.org, jiangkunkun@huawei.com
Subject: [PATCH v13 04/13] vfio/pci: Add VFIO_REGION_TYPE_NESTED region type
Date: Sun, 11 Apr 2021 13:46:50 +0200 [thread overview]
Message-ID: <20210411114659.15051-5-eric.auger@redhat.com> (raw)
In-Reply-To: <20210411114659.15051-1-eric.auger@redhat.com>
Add a new specific DMA_FAULT region aiming to exposed nested mode
translation faults. This region only is exposed if the device
is attached to a nested domain.
The region has a ring buffer that contains the actual fault
records plus a header allowing to handle it (tail/head indices,
max capacity, entry size). At the moment the region is dimensionned
for 512 fault records.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
v11 -> v12:
- set fault_pages to NULL after free
- check new_tail >= header->nb_entries (Zenghui)
- update value of VFIO_REGION_TYPE_NESTED
- handle the case where the domain is NULL
- pass an int pointer to iommu_domain_get_attr [Shenming]
v10 -> v11:
- rename vfio_pci_init_dma_fault_region into
vfio_pci_dma_fault_init
- free fault_pages in vfio_pci_dma_fault_release
- only register the region if the device is attached
to a nested domain
v8 -> v9:
- Use a single region instead of a prod/cons region
v4 -> v5
- check cons is not null in vfio_pci_check_cons_fault
v3 -> v4:
- use 2 separate regions, respectively in read and write modes
- add the version capability
---
drivers/vfio/pci/vfio_pci.c | 79 +++++++++++++++++++++++++++++
drivers/vfio/pci/vfio_pci_private.h | 6 +++
drivers/vfio/pci/vfio_pci_rdwr.c | 44 ++++++++++++++++
include/uapi/linux/vfio.h | 35 +++++++++++++
4 files changed, 164 insertions(+)
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 65e7e6b44578..f37cabddf1d6 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -309,6 +309,81 @@ int vfio_pci_set_power_state(struct vfio_pci_device *vdev, pci_power_t state)
return ret;
}
+static void vfio_pci_dma_fault_release(struct vfio_pci_device *vdev,
+ struct vfio_pci_region *region)
+{
+ kfree(vdev->fault_pages);
+}
+
+static int vfio_pci_dma_fault_add_capability(struct vfio_pci_device *vdev,
+ struct vfio_pci_region *region,
+ struct vfio_info_cap *caps)
+{
+ struct vfio_region_info_cap_fault cap = {
+ .header.id = VFIO_REGION_INFO_CAP_DMA_FAULT,
+ .header.version = 1,
+ .version = 1,
+ };
+ return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
+}
+
+static const struct vfio_pci_regops vfio_pci_dma_fault_regops = {
+ .rw = vfio_pci_dma_fault_rw,
+ .release = vfio_pci_dma_fault_release,
+ .add_capability = vfio_pci_dma_fault_add_capability,
+};
+
+#define DMA_FAULT_RING_LENGTH 512
+
+static int vfio_pci_dma_fault_init(struct vfio_pci_device *vdev)
+{
+ struct vfio_region_dma_fault *header;
+ struct iommu_domain *domain;
+ size_t size;
+ int nested;
+ int ret;
+
+ domain = iommu_get_domain_for_dev(&vdev->pdev->dev);
+ if (!domain)
+ return 0;
+
+ ret = iommu_domain_get_attr(domain, DOMAIN_ATTR_NESTING, &nested);
+ if (ret || !nested)
+ return ret;
+
+ mutex_init(&vdev->fault_queue_lock);
+
+ /*
+ * We provision 1 page for the header and space for
+ * DMA_FAULT_RING_LENGTH fault records in the ring buffer.
+ */
+ size = ALIGN(sizeof(struct iommu_fault) *
+ DMA_FAULT_RING_LENGTH, PAGE_SIZE) + PAGE_SIZE;
+
+ vdev->fault_pages = kzalloc(size, GFP_KERNEL);
+ if (!vdev->fault_pages)
+ return -ENOMEM;
+
+ ret = vfio_pci_register_dev_region(vdev,
+ VFIO_REGION_TYPE_NESTED,
+ VFIO_REGION_SUBTYPE_NESTED_DMA_FAULT,
+ &vfio_pci_dma_fault_regops, size,
+ VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE,
+ vdev->fault_pages);
+ if (ret)
+ goto out;
+
+ header = (struct vfio_region_dma_fault *)vdev->fault_pages;
+ header->entry_size = sizeof(struct iommu_fault);
+ header->nb_entries = DMA_FAULT_RING_LENGTH;
+ header->offset = sizeof(struct vfio_region_dma_fault);
+ return 0;
+out:
+ kfree(vdev->fault_pages);
+ vdev->fault_pages = NULL;
+ return ret;
+}
+
static int vfio_pci_enable(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
@@ -407,6 +482,10 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
}
}
+ ret = vfio_pci_dma_fault_init(vdev);
+ if (ret)
+ goto disable_exit;
+
vfio_pci_probe_mmaps(vdev);
return 0;
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 9cd1882a05af..76cb3bd11375 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -134,6 +134,8 @@ struct vfio_pci_device {
int ioeventfds_nr;
struct eventfd_ctx *err_trigger;
struct eventfd_ctx *req_trigger;
+ u8 *fault_pages;
+ struct mutex fault_queue_lock;
struct list_head dummy_resources_list;
struct mutex ioeventfds_lock;
struct list_head ioeventfds_list;
@@ -170,6 +172,10 @@ extern ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
extern long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset,
uint64_t data, int count, int fd);
+extern size_t vfio_pci_dma_fault_rw(struct vfio_pci_device *vdev,
+ char __user *buf, size_t count,
+ loff_t *ppos, bool iswrite);
+
extern int vfio_pci_init_perm_bits(void);
extern void vfio_pci_uninit_perm_bits(void);
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index a0b5fc8e46f4..164120607469 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -356,6 +356,50 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
return done;
}
+size_t vfio_pci_dma_fault_rw(struct vfio_pci_device *vdev, char __user *buf,
+ size_t count, loff_t *ppos, bool iswrite)
+{
+ unsigned int i = VFIO_PCI_OFFSET_TO_INDEX(*ppos) - VFIO_PCI_NUM_REGIONS;
+ loff_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+ void *base = vdev->region[i].data;
+ int ret = -EFAULT;
+
+ if (pos >= vdev->region[i].size)
+ return -EINVAL;
+
+ count = min(count, (size_t)(vdev->region[i].size - pos));
+
+ mutex_lock(&vdev->fault_queue_lock);
+
+ if (iswrite) {
+ struct vfio_region_dma_fault *header =
+ (struct vfio_region_dma_fault *)base;
+ u32 new_tail;
+
+ if (pos != 0 || count != 4) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ if (copy_from_user((void *)&new_tail, buf, count))
+ goto unlock;
+
+ if (new_tail >= header->nb_entries) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+ header->tail = new_tail;
+ } else {
+ if (copy_to_user(buf, base + pos, count))
+ goto unlock;
+ }
+ *ppos += count;
+ ret = count;
+unlock:
+ mutex_unlock(&vdev->fault_queue_lock);
+ return ret;
+}
+
static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd,
bool test_mem)
{
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index afa8596c05d2..ca8cc796e254 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -325,6 +325,7 @@ struct vfio_region_info_cap_type {
#define VFIO_REGION_TYPE_GFX (1)
#define VFIO_REGION_TYPE_CCW (2)
#define VFIO_REGION_TYPE_MIGRATION (3)
+#define VFIO_REGION_TYPE_NESTED (4)
/* sub-types for VFIO_REGION_TYPE_PCI_* */
@@ -349,6 +350,9 @@ struct vfio_region_info_cap_type {
/* sub-types for VFIO_REGION_TYPE_GFX */
#define VFIO_REGION_SUBTYPE_GFX_EDID (1)
+/* sub-types for VFIO_REGION_TYPE_NESTED */
+#define VFIO_REGION_SUBTYPE_NESTED_DMA_FAULT (1)
+
/**
* struct vfio_region_gfx_edid - EDID region layout.
*
@@ -995,6 +999,37 @@ struct vfio_device_feature {
*/
#define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN (0)
+/*
+ * Capability exposed by the DMA fault region
+ * @version: ABI version
+ */
+#define VFIO_REGION_INFO_CAP_DMA_FAULT 6
+
+struct vfio_region_info_cap_fault {
+ struct vfio_info_cap_header header;
+ __u32 version;
+};
+
+/*
+ * DMA Fault Region Layout
+ * @tail: index relative to the start of the ring buffer at which the
+ * consumer finds the next item in the buffer
+ * @entry_size: fault ring buffer entry size in bytes
+ * @nb_entries: max capacity of the fault ring buffer
+ * @offset: ring buffer offset relative to the start of the region
+ * @head: index relative to the start of the ring buffer at which the
+ * producer (kernel) inserts items into the buffers
+ */
+struct vfio_region_dma_fault {
+ /* Write-Only */
+ __u32 tail;
+ /* Read-Only */
+ __u32 entry_size;
+ __u32 nb_entries;
+ __u32 offset;
+ __u32 head;
+};
+
/* -------- API for Type1 VFIO IOMMU -------- */
/**
--
2.26.3
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2021-04-11 11:48 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-11 11:46 [PATCH v13 00/13] SMMUv3 Nested Stage Setup (VFIO part) Eric Auger
2021-04-11 11:46 ` [PATCH v13 01/13] vfio: VFIO_IOMMU_SET_PASID_TABLE Eric Auger
2021-04-11 14:12 ` kernel test robot
2021-04-11 14:35 ` kernel test robot
2021-04-11 11:46 ` [PATCH v13 02/13] vfio: VFIO_IOMMU_CACHE_INVALIDATE Eric Auger
2021-04-11 11:46 ` [PATCH v13 03/13] vfio: VFIO_IOMMU_SET_MSI_BINDING Eric Auger
2021-04-11 15:28 ` kernel test robot
2021-04-11 11:46 ` Eric Auger [this message]
2021-04-11 11:46 ` [PATCH v13 05/13] vfio/pci: Register an iommu fault handler Eric Auger
2021-04-11 11:46 ` [PATCH v13 06/13] vfio/pci: Allow to mmap the fault queue Eric Auger
2021-04-11 11:46 ` [PATCH v13 07/13] vfio: Use capability chains to handle device specific irq Eric Auger
2021-04-11 11:46 ` [PATCH v13 08/13] vfio/pci: Add framework for custom interrupt indices Eric Auger
2021-04-11 11:46 ` [PATCH v13 09/13] vfio: Add new IRQ for DMA fault reporting Eric Auger
2021-04-11 11:46 ` [PATCH v13 10/13] vfio/pci: Register and allow DMA FAULT IRQ signaling Eric Auger
2021-04-11 11:46 ` [PATCH v13 11/13] vfio: Document nested stage control Eric Auger
2021-04-11 11:46 ` [PATCH v13 12/13] vfio/pci: Register a DMA fault response region Eric Auger
2021-04-11 11:46 ` [PATCH v13 13/13] vfio/pci: Inject page response upon response region fill Eric Auger
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=20210411114659.15051-5-eric.auger@redhat.com \
--to=eric.auger@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=eric.auger.pro@gmail.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jean-philippe@linaro.org \
--cc=jiangkunkun@huawei.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-kernel@vger.kernel.org \
--cc=lushenming@huawei.com \
--cc=maz@kernel.org \
--cc=robin.murphy@arm.com \
--cc=tn@semihalf.com \
--cc=vivek.gautam@arm.com \
--cc=vsethi@nvidia.com \
--cc=wangxingang5@huawei.com \
--cc=will@kernel.org \
--cc=zhangfei.gao@linaro.org \
--cc=zhukeqian1@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).