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 2/8] vfio/type1: Add a page fault handler
Date: Fri, 9 Apr 2021 11:44:14 +0800 [thread overview]
Message-ID: <20210409034420.1799-3-lushenming@huawei.com> (raw)
In-Reply-To: <20210409034420.1799-1-lushenming@huawei.com>
VFIO manages the DMA mapping itself. To support IOPF (on-demand paging)
for VFIO (IOMMU capable) devices, we add a VFIO page fault handler to
serve the reported page faults from the IOMMU driver.
Signed-off-by: Shenming Lu <lushenming@huawei.com>
---
drivers/vfio/vfio_iommu_type1.c | 114 ++++++++++++++++++++++++++++++++
1 file changed, 114 insertions(+)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 45cbfd4879a5..ab0ff60ee207 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -101,6 +101,7 @@ struct vfio_dma {
struct task_struct *task;
struct rb_root pfn_list; /* Ex-user pinned pfn list */
unsigned long *bitmap;
+ unsigned long *iopf_mapped_bitmap;
};
struct vfio_batch {
@@ -141,6 +142,16 @@ struct vfio_regions {
size_t len;
};
+/* A global IOPF enabled group list */
+static struct rb_root iopf_group_list = RB_ROOT;
+static DEFINE_MUTEX(iopf_group_list_lock);
+
+struct vfio_iopf_group {
+ struct rb_node node;
+ struct iommu_group *iommu_group;
+ struct vfio_iommu *iommu;
+};
+
#define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu) \
(!list_empty(&iommu->domain_list))
@@ -157,6 +168,10 @@ struct vfio_regions {
#define DIRTY_BITMAP_PAGES_MAX ((u64)INT_MAX)
#define DIRTY_BITMAP_SIZE_MAX DIRTY_BITMAP_BYTES(DIRTY_BITMAP_PAGES_MAX)
+#define IOPF_MAPPED_BITMAP_GET(dma, i) \
+ ((dma->iopf_mapped_bitmap[(i) / BITS_PER_LONG] \
+ >> ((i) % BITS_PER_LONG)) & 0x1)
+
#define WAITED 1
static int put_pfn(unsigned long pfn, int prot);
@@ -416,6 +431,34 @@ static int vfio_iova_put_vfio_pfn(struct vfio_dma *dma, struct vfio_pfn *vpfn)
return ret;
}
+/*
+ * Helper functions for iopf_group_list
+ */
+static struct vfio_iopf_group *
+vfio_find_iopf_group(struct iommu_group *iommu_group)
+{
+ struct vfio_iopf_group *iopf_group;
+ struct rb_node *node;
+
+ mutex_lock(&iopf_group_list_lock);
+
+ node = iopf_group_list.rb_node;
+
+ while (node) {
+ iopf_group = rb_entry(node, struct vfio_iopf_group, node);
+
+ if (iommu_group < iopf_group->iommu_group)
+ node = node->rb_left;
+ else if (iommu_group > iopf_group->iommu_group)
+ node = node->rb_right;
+ else
+ break;
+ }
+
+ mutex_unlock(&iopf_group_list_lock);
+ return node ? iopf_group : NULL;
+}
+
static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async)
{
struct mm_struct *mm;
@@ -3106,6 +3149,77 @@ static int vfio_iommu_type1_dirty_pages(struct vfio_iommu *iommu,
return -EINVAL;
}
+/* VFIO I/O Page Fault handler */
+static int vfio_iommu_type1_dma_map_iopf(struct iommu_fault *fault, void *data)
+{
+ struct device *dev = (struct device *)data;
+ struct iommu_group *iommu_group;
+ struct vfio_iopf_group *iopf_group;
+ struct vfio_iommu *iommu;
+ struct vfio_dma *dma;
+ dma_addr_t iova = ALIGN_DOWN(fault->prm.addr, PAGE_SIZE);
+ int access_flags = 0;
+ unsigned long bit_offset, vaddr, pfn;
+ int ret;
+ enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
+ struct iommu_page_response resp = {0};
+
+ if (fault->type != IOMMU_FAULT_PAGE_REQ)
+ return -EOPNOTSUPP;
+
+ iommu_group = iommu_group_get(dev);
+ if (!iommu_group)
+ return -ENODEV;
+
+ iopf_group = vfio_find_iopf_group(iommu_group);
+ iommu_group_put(iommu_group);
+ if (!iopf_group)
+ return -ENODEV;
+
+ iommu = iopf_group->iommu;
+
+ mutex_lock(&iommu->lock);
+
+ ret = vfio_find_dma_valid(iommu, iova, PAGE_SIZE, &dma);
+ if (ret < 0)
+ goto out_invalid;
+
+ if (fault->prm.perm & IOMMU_FAULT_PERM_READ)
+ access_flags |= IOMMU_READ;
+ if (fault->prm.perm & IOMMU_FAULT_PERM_WRITE)
+ access_flags |= IOMMU_WRITE;
+ if ((dma->prot & access_flags) != access_flags)
+ goto out_invalid;
+
+ bit_offset = (iova - dma->iova) >> PAGE_SHIFT;
+ if (IOPF_MAPPED_BITMAP_GET(dma, bit_offset))
+ goto out_success;
+
+ vaddr = iova - dma->iova + dma->vaddr;
+
+ if (vfio_pin_page_external(dma, vaddr, &pfn, true))
+ goto out_invalid;
+
+ if (vfio_iommu_map(iommu, iova, pfn, 1, dma->prot)) {
+ if (put_pfn(pfn, dma->prot))
+ vfio_lock_acct(dma, -1, true);
+ goto out_invalid;
+ }
+
+ bitmap_set(dma->iopf_mapped_bitmap, bit_offset, 1);
+
+out_success:
+ status = IOMMU_PAGE_RESP_SUCCESS;
+
+out_invalid:
+ mutex_unlock(&iommu->lock);
+ resp.version = IOMMU_PAGE_RESP_VERSION_1;
+ resp.grpid = fault->prm.grpid;
+ resp.code = status;
+ iommu_page_response(dev, &resp);
+ return 0;
+}
+
static long vfio_iommu_type1_ioctl(void *iommu_data,
unsigned int cmd, unsigned long arg)
{
--
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 ` Shenming Lu [this message]
2021-05-18 18:58 ` [RFC PATCH v3 2/8] vfio/type1: Add a page fault handler 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 ` [RFC PATCH v3 8/8] vfio: Add nested IOPF support Shenming Lu
2021-05-18 18:58 ` 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=20210409034420.1799-3-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).