From: Peter Xu <peterx@redhat.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Christophe de Dinechin <dinechin@redhat.com>,
"Michael S . Tsirkin" <mst@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <sean.j.christopherson@intel.com>,
Yan Zhao <yan.y.zhao@intel.com>,
Alex Williamson <alex.williamson@redhat.com>,
Jason Wang <jasowang@redhat.com>,
Kevin Kevin <kevin.tian@intel.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
peterx@redhat.com,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>
Subject: [PATCH v3 01/21] vfio: introduce vfio_iova_rw to read/write a range of IOVAs
Date: Thu, 9 Jan 2020 09:57:09 -0500 [thread overview]
Message-ID: <20200109145729.32898-2-peterx@redhat.com> (raw)
In-Reply-To: <20200109145729.32898-1-peterx@redhat.com>
From: Yan Zhao <yan.y.zhao@intel.com>
vfio_iova_rw will read/write a range of userspace memory (starting form
device iova to iova + len -1) into a kenrel buffer without pinning the
userspace memory.
TODO: vfio needs to mark the iova dirty if vfio_iova_rw(write) is
called.
Cc: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
drivers/vfio/vfio.c | 45 ++++++++++++++++++
drivers/vfio/vfio_iommu_type1.c | 81 +++++++++++++++++++++++++++++++++
include/linux/vfio.h | 5 ++
3 files changed, 131 insertions(+)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index c8482624ca34..36e91e647ed5 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1961,6 +1961,51 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage)
}
EXPORT_SYMBOL(vfio_unpin_pages);
+/*
+ * Read/Write a range of userspace IOVAs for a device into/from a kernel
+ * buffer without pinning the userspace memory
+ * @dev [in] : device
+ * @iova [in] : base IOVA of a userspace buffer
+ * @data [in] : pointer to kernel buffer
+ * @len [in] : kernel buffer length
+ * @write : indicate read or write
+ * Return error on failure or 0 on success.
+ */
+int vfio_iova_rw(struct device *dev, unsigned long iova, void *data,
+ unsigned long len, bool write)
+{
+ struct vfio_container *container;
+ struct vfio_group *group;
+ struct vfio_iommu_driver *driver;
+ int ret = 0;
+
+ if (!dev || !data || len <= 0)
+ 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->iova_rw))
+ ret = driver->ops->iova_rw(container->iommu_data,
+ iova, data, len, write);
+ else
+ ret = -ENOTTY;
+
+ vfio_group_try_dissolve_container(group);
+out:
+ vfio_group_put(group);
+ return ret;
+}
+EXPORT_SYMBOL(vfio_iova_rw);
+
static int vfio_register_iommu_notifier(struct vfio_group *group,
unsigned long *events,
struct notifier_block *nb)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 2ada8e6cdb88..aee191077235 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -27,6 +27,7 @@
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/mm.h>
+#include <linux/mmu_context.h>
#include <linux/rbtree.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
@@ -2326,6 +2327,85 @@ static int vfio_iommu_type1_unregister_notifier(void *iommu_data,
return blocking_notifier_chain_unregister(&iommu->notifier, nb);
}
+static int next_segment(unsigned long len, int offset)
+{
+ if (len > PAGE_SIZE - offset)
+ return PAGE_SIZE - offset;
+ else
+ return len;
+}
+
+static int vfio_iommu_type1_rw_iova_seg(struct vfio_iommu *iommu,
+ unsigned long iova, void *data,
+ unsigned long seg_len,
+ unsigned long offset,
+ bool write)
+{
+ struct mm_struct *mm;
+ unsigned long vaddr;
+ struct vfio_dma *dma;
+ bool kthread = current->mm == NULL;
+ int ret = 0;
+
+ dma = vfio_find_dma(iommu, iova, PAGE_SIZE);
+ if (!dma)
+ return -EINVAL;
+
+ mm = get_task_mm(dma->task);
+
+ if (!mm)
+ return -ENODEV;
+
+ if (kthread)
+ use_mm(mm);
+ else if (current->mm != mm) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ vaddr = dma->vaddr + iova - dma->iova + offset;
+
+ ret = write ? __copy_to_user((void __user *)vaddr,
+ data, seg_len) :
+ __copy_from_user(data, (void __user *)vaddr,
+ seg_len);
+ if (ret)
+ ret = -EFAULT;
+
+ if (kthread)
+ unuse_mm(mm);
+out:
+ mmput(mm);
+ return ret;
+}
+
+static int vfio_iommu_type1_iova_rw(void *iommu_data, unsigned long iova,
+ void *data, unsigned long len, bool write)
+{
+ struct vfio_iommu *iommu = iommu_data;
+ int offset = iova & ~PAGE_MASK;
+ int seg_len;
+ int ret = 0;
+
+ iova = iova & PAGE_MASK;
+
+ mutex_lock(&iommu->lock);
+ while ((seg_len = next_segment(len, offset)) > 0) {
+ ret = vfio_iommu_type1_rw_iova_seg(iommu, iova, data,
+ seg_len, offset, write);
+ if (ret)
+ break;
+
+ offset = 0;
+ len -= seg_len;
+ data += seg_len;
+ iova += PAGE_SIZE;
+ }
+
+ mutex_unlock(&iommu->lock);
+ return ret;
+}
+
static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
.name = "vfio-iommu-type1",
.owner = THIS_MODULE,
@@ -2338,6 +2418,7 @@ static const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_type1 = {
.unpin_pages = vfio_iommu_type1_unpin_pages,
.register_notifier = vfio_iommu_type1_register_notifier,
.unregister_notifier = vfio_iommu_type1_unregister_notifier,
+ .iova_rw = vfio_iommu_type1_iova_rw,
};
static int __init vfio_iommu_type1_init(void)
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index e42a711a2800..7bf18a31bbcf 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -82,6 +82,8 @@ struct vfio_iommu_driver_ops {
struct notifier_block *nb);
int (*unregister_notifier)(void *iommu_data,
struct notifier_block *nb);
+ int (*iova_rw)(void *iommu_data, unsigned long iova,
+ void *data, unsigned long len, bool write);
};
extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
@@ -107,6 +109,9 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
int npage);
+extern int vfio_iova_rw(struct device *dev, unsigned long iova, void *data,
+ unsigned long len, bool write);
+
/* each type has independent events */
enum vfio_notify_type {
VFIO_IOMMU_NOTIFY = 0,
--
2.24.1
next prev parent reply other threads:[~2020-01-09 14:57 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-09 14:57 [PATCH v3 00/21] KVM: Dirty ring interface Peter Xu
2020-01-09 14:57 ` Peter Xu [this message]
2020-01-09 14:57 ` [PATCH v3 02/21] drm/i915/gvt: subsitute kvm_read/write_guest with vfio_iova_rw Peter Xu
2020-01-09 14:57 ` [PATCH v3 03/21] KVM: Remove kvm_read_guest_atomic() Peter Xu
2020-01-09 14:57 ` [PATCH v3 04/21] KVM: Add build-time error check on kvm_run size Peter Xu
2020-01-09 14:57 ` [PATCH v3 05/21] KVM: X86: Change parameter for fast_page_fault tracepoint Peter Xu
2020-01-09 14:57 ` [PATCH v3 06/21] KVM: X86: Don't take srcu lock in init_rmode_identity_map() Peter Xu
2020-01-09 14:57 ` [PATCH v3 07/21] KVM: Cache as_id in kvm_memory_slot Peter Xu
2020-01-09 14:57 ` [PATCH v3 08/21] KVM: X86: Drop x86_set_memory_region() Peter Xu
2020-01-09 14:57 ` [PATCH v3 09/21] KVM: X86: Don't track dirty for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR] Peter Xu
2020-01-19 9:01 ` Paolo Bonzini
2020-01-20 6:45 ` Peter Xu
2020-01-21 15:56 ` Sean Christopherson
2020-01-21 16:14 ` Paolo Bonzini
2020-01-28 5:50 ` Peter Xu
2020-01-28 18:24 ` Sean Christopherson
2020-01-31 15:08 ` Peter Xu
2020-01-31 19:33 ` Sean Christopherson
2020-01-31 20:28 ` Peter Xu
2020-01-31 20:36 ` Sean Christopherson
2020-01-31 20:55 ` Peter Xu
2020-01-31 21:29 ` Sean Christopherson
2020-01-31 22:16 ` Peter Xu
2020-01-31 22:20 ` Sean Christopherson
2020-01-09 14:57 ` [PATCH v3 10/21] KVM: Pass in kvm pointer into mark_page_dirty_in_slot() Peter Xu
2020-01-09 14:57 ` [PATCH v3 11/21] KVM: Move running VCPU from ARM to common code Peter Xu
2020-01-09 14:57 ` [PATCH v3 12/21] KVM: X86: Implement ring-based dirty memory tracking Peter Xu
2020-01-09 16:29 ` Michael S. Tsirkin
2020-01-09 16:56 ` Alex Williamson
2020-01-09 19:21 ` Peter Xu
2020-01-09 19:36 ` Michael S. Tsirkin
2020-01-09 19:15 ` Peter Xu
2020-01-09 19:35 ` Michael S. Tsirkin
2020-01-09 20:19 ` Peter Xu
2020-01-09 22:18 ` Michael S. Tsirkin
2020-01-10 15:29 ` Peter Xu
2020-01-12 6:24 ` Michael S. Tsirkin
2020-01-14 20:01 ` Peter Xu
2020-01-15 6:50 ` Michael S. Tsirkin
2020-01-15 15:20 ` Peter Xu
2020-01-19 9:09 ` Paolo Bonzini
2020-01-19 10:12 ` Michael S. Tsirkin
2020-01-20 7:29 ` Peter Xu
2020-01-20 7:47 ` Michael S. Tsirkin
2020-01-21 8:29 ` Peter Xu
2020-01-21 10:25 ` Paolo Bonzini
2020-01-21 10:24 ` Paolo Bonzini
2020-01-11 4:49 ` kbuild test robot
2020-01-11 23:19 ` kbuild test robot
2020-01-15 6:47 ` Michael S. Tsirkin
2020-01-15 15:27 ` Peter Xu
2020-01-16 8:38 ` Michael S. Tsirkin
2020-01-16 16:27 ` Peter Xu
2020-01-17 9:50 ` Michael S. Tsirkin
2020-01-20 6:48 ` Peter Xu
2020-01-09 14:57 ` [PATCH v3 13/21] KVM: Make dirty ring exclusive to dirty bitmap log Peter Xu
2020-01-09 14:57 ` [PATCH v3 14/21] KVM: Don't allocate dirty bitmap if dirty ring is enabled Peter Xu
2020-01-09 16:41 ` Peter Xu
2020-01-09 14:57 ` [PATCH v3 15/21] KVM: selftests: Always clear dirty bitmap after iteration Peter Xu
2020-01-09 14:57 ` [PATCH v3 16/21] KVM: selftests: Sync uapi/linux/kvm.h to tools/ Peter Xu
2020-01-09 14:57 ` [PATCH v3 17/21] KVM: selftests: Use a single binary for dirty/clear log test Peter Xu
2020-01-09 14:57 ` [PATCH v3 18/21] KVM: selftests: Introduce after_vcpu_run hook for dirty " Peter Xu
2020-01-09 14:57 ` [PATCH v3 19/21] KVM: selftests: Add dirty ring buffer test Peter Xu
2020-01-09 14:57 ` [PATCH v3 20/21] KVM: selftests: Let dirty_log_test async for dirty ring test Peter Xu
2020-01-09 14:57 ` [PATCH v3 21/21] KVM: selftests: Add "-c" parameter to dirty log test Peter Xu
2020-01-09 15:59 ` [PATCH v3 00/21] KVM: Dirty ring interface Michael S. Tsirkin
2020-01-09 16:17 ` Peter Xu
2020-01-09 16:40 ` Michael S. Tsirkin
2020-01-09 17:08 ` Peter Xu
2020-01-09 19:08 ` Michael S. Tsirkin
2020-01-09 19:39 ` Peter Xu
2020-01-09 20:42 ` Paolo Bonzini
2020-01-09 22:28 ` Michael S. Tsirkin
2020-01-10 15:10 ` Peter Xu
2020-01-09 16:47 ` Alex Williamson
2020-01-09 17:58 ` Peter Xu
2020-01-09 19:13 ` Michael S. Tsirkin
2020-01-09 19:23 ` Peter Xu
2020-01-09 19:37 ` Michael S. Tsirkin
2020-01-09 20:51 ` Paolo Bonzini
2020-01-09 22:21 ` Michael S. Tsirkin
2020-01-19 9:11 ` Paolo Bonzini
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=20200109145729.32898-2-peterx@redhat.com \
--to=peterx@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=dgilbert@redhat.com \
--cc=dinechin@redhat.com \
--cc=jasowang@redhat.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=vkuznets@redhat.com \
--cc=yan.y.zhao@intel.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).