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,
joro@8bytes.org, alex.williamson@redhat.com,
jacob.jun.pan@linux.intel.com, yi.l.liu@intel.com,
jean-philippe.brucker@arm.com, will.deacon@arm.com,
robin.murphy@arm.com
Cc: kevin.tian@intel.com, ashok.raj@intel.com, marc.zyngier@arm.com,
peter.maydell@linaro.org, vincent.stehle@arm.com,
zhangfei.gao@gmail.com, tina.zhang@intel.com
Subject: [PATCH v9 04/11] vfio/pci: Add VFIO_REGION_TYPE_NESTED region type
Date: Thu, 11 Jul 2019 15:56:18 +0200 [thread overview]
Message-ID: <20190711135625.20684-5-eric.auger@redhat.com> (raw)
In-Reply-To: <20190711135625.20684-1-eric.auger@redhat.com>
Add a new specific DMA_FAULT region aiming to exposed nested mode
translation faults.
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>
---
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 | 68 +++++++++++++++++++++++++++++
drivers/vfio/pci/vfio_pci_private.h | 10 +++++
drivers/vfio/pci/vfio_pci_rdwr.c | 45 +++++++++++++++++++
include/uapi/linux/vfio.h | 35 +++++++++++++++
4 files changed, 158 insertions(+)
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 703948c9fbe1..3b091cfdaf46 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -258,6 +258,69 @@ 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)
+{
+}
+
+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_init_dma_fault_region(struct vfio_pci_device *vdev)
+{
+ struct vfio_region_dma_fault *header;
+ size_t size;
+ int 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);
+ return ret;
+}
+
static int vfio_pci_enable(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
@@ -356,6 +419,10 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
}
}
+ ret = vfio_pci_init_dma_fault_region(vdev);
+ if (ret)
+ goto disable_exit;
+
vfio_pci_probe_mmaps(vdev);
return 0;
@@ -1371,6 +1438,7 @@ static void vfio_pci_remove(struct pci_dev *pdev)
vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev);
kfree(vdev->region);
+ kfree(vdev->fault_pages);
mutex_destroy(&vdev->ioeventfds_lock);
if (!disable_idle_d3)
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index ee6ee91718a4..fde40db3cd34 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -119,6 +119,8 @@ 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;
@@ -150,6 +152,14 @@ 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);
+struct vfio_pci_fault_abi {
+ u32 entry_size;
+};
+
+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 0120d8324a40..829c5284c6be 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -274,6 +274,51 @@ 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 int vfio_pci_ioeventfd_handler(void *opaque, void *unused)
{
struct vfio_pci_ioeventfd *ioeventfd = opaque;
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index deadbd84f2cf..bec761edae9b 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -307,6 +307,9 @@ struct vfio_region_info_cap_type {
#define VFIO_REGION_TYPE_GFX (1)
#define VFIO_REGION_SUBTYPE_GFX_EDID (1)
+#define VFIO_REGION_TYPE_NESTED (2)
+#define VFIO_REGION_SUBTYPE_NESTED_DMA_FAULT (1)
+
/**
* struct vfio_region_gfx_edid - EDID region layout.
*
@@ -701,6 +704,38 @@ struct vfio_device_ioeventfd {
#define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16)
+
+/*
+ * 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 -------- */
/**
--
2.20.1
next prev parent reply other threads:[~2019-07-11 13:57 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-11 13:56 [PATCH v9 00/11] SMMUv3 Nested Stage Setup (VFIO part) Eric Auger
2019-07-11 13:56 ` [PATCH v9 01/11] vfio: VFIO_IOMMU_SET_PASID_TABLE Eric Auger
2019-07-11 13:56 ` [PATCH v9 02/11] vfio: VFIO_IOMMU_CACHE_INVALIDATE Eric Auger
2019-07-11 13:56 ` [PATCH v9 03/11] vfio: VFIO_IOMMU_SET_MSI_BINDING Eric Auger
2019-07-11 13:56 ` Eric Auger [this message]
2019-07-11 13:56 ` [PATCH v9 05/11] vfio/pci: Register an iommu fault handler Eric Auger
2019-07-11 13:56 ` [PATCH v9 06/11] vfio/pci: Allow to mmap the fault queue Eric Auger
2019-07-11 13:56 ` [PATCH v9 07/11] vfio: Use capability chains to handle device specific irq Eric Auger
2019-07-11 13:56 ` [PATCH v9 08/11] vfio: Add new IRQ for DMA fault reporting Eric Auger
2019-07-11 13:56 ` [PATCH v9 09/11] vfio/pci: Add framework for custom interrupt indices Eric Auger
2019-07-11 13:56 ` [PATCH v9 10/11] vfio/pci: Register and allow DMA FAULT IRQ signaling Eric Auger
2019-07-11 13:56 ` [PATCH v9 11/11] vfio: Document nested stage control Eric Auger
2019-11-12 11:08 ` [PATCH v9 00/11] SMMUv3 Nested Stage Setup (VFIO part) Shameerali Kolothum Thodi
2019-11-12 11:28 ` Auger Eric
2019-11-12 13:06 ` Shameerali Kolothum Thodi
2019-11-12 13:21 ` Auger Eric
2019-11-12 14:21 ` Shameerali Kolothum Thodi
2019-11-12 17:56 ` Shameerali Kolothum Thodi
2019-11-12 20:34 ` Auger Eric
2019-11-13 16:24 ` Shameerali Kolothum Thodi
2019-11-20 8:15 ` Tomasz Nowicki
2019-11-20 10:18 ` Auger Eric
2020-03-03 12:57 ` zhangfei
2020-03-03 13:14 ` Auger Eric
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=20190711135625.20684-5-eric.auger@redhat.com \
--to=eric.auger@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=ashok.raj@intel.com \
--cc=eric.auger.pro@gmail.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jean-philippe.brucker@arm.com \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-kernel@vger.kernel.org \
--cc=marc.zyngier@arm.com \
--cc=peter.maydell@linaro.org \
--cc=robin.murphy@arm.com \
--cc=tina.zhang@intel.com \
--cc=vincent.stehle@arm.com \
--cc=will.deacon@arm.com \
--cc=yi.l.liu@intel.com \
--cc=zhangfei.gao@gmail.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).