From: Yi Liu <yi.l.liu@intel.com>
To: alex.williamson@redhat.com, jgg@nvidia.com, kevin.tian@intel.com
Cc: joro@8bytes.org, robin.murphy@arm.com, cohuck@redhat.com,
eric.auger@redhat.com, nicolinc@nvidia.com, kvm@vger.kernel.org,
mjrosato@linux.ibm.com, chao.p.peng@linux.intel.com,
yi.l.liu@intel.com, yi.y.sun@linux.intel.com, peterx@redhat.com,
jasowang@redhat.com, shameerali.kolothum.thodi@huawei.com,
lulu@redhat.com, suravee.suthikulpanit@amd.com,
intel-gvt-dev@lists.freedesktop.org,
intel-gfx@lists.freedesktop.org, linux-s390@vger.kernel.org,
xudong.hao@intel.com, yan.y.zhao@intel.com,
terrence.xu@intel.com, yanting.jiang@intel.com,
zhenzhong.duan@intel.com, clegoate@redhat.com
Subject: [PATCH v8 09/10] vfio/pci: Copy hot-reset device info to userspace in the devices loop
Date: Fri, 16 Jun 2023 02:30:41 -0700 [thread overview]
Message-ID: <20230616093042.65094-10-yi.l.liu@intel.com> (raw)
In-Reply-To: <20230616093042.65094-1-yi.l.liu@intel.com>
This copies the vfio_pci_dependent_device to userspace during looping each
affected device for reporting vfio_pci_hot_reset_info. This avoids counting
the affected devices and allocating a potential large buffer to store the
vfio_pci_dependent_device of all the affected devices before copying them
to userspace.
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
---
drivers/vfio/pci/vfio_pci_core.c | 93 ++++++++++++--------------------
1 file changed, 33 insertions(+), 60 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 65e3ee5255a6..5998da0f5771 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -777,19 +777,25 @@ static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
}
struct vfio_pci_fill_info {
- int max;
- int cur;
- struct vfio_pci_dependent_device *devices;
+ struct vfio_pci_dependent_device __user *devices;
+ struct vfio_pci_dependent_device __user *devices_end;
struct vfio_device *vdev;
+ u32 count;
u32 flags;
};
static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
{
+ struct vfio_pci_dependent_device info = {
+ .segment = pci_domain_nr(pdev->bus),
+ .bus = pdev->bus->number,
+ .devfn = pdev->devfn,
+ };
struct vfio_pci_fill_info *fill = data;
- if (fill->cur == fill->max)
- return -EAGAIN; /* Something changed, try again */
+ fill->count++;
+ if (fill->devices >= fill->devices_end)
+ return 0;
if (fill->flags & VFIO_PCI_HOT_RESET_FLAG_DEV_ID) {
struct iommufd_ctx *iommufd = vfio_iommufd_device_ictx(fill->vdev);
@@ -802,19 +808,19 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
*/
vdev = vfio_find_device_in_devset(dev_set, &pdev->dev);
if (!vdev) {
- fill->devices[fill->cur].devid = VFIO_PCI_DEVID_NOT_OWNED;
+ info.devid = VFIO_PCI_DEVID_NOT_OWNED;
} else {
int id = vfio_iommufd_get_dev_id(vdev, iommufd);
if (id > 0)
- fill->devices[fill->cur].devid = id;
+ info.devid = id;
else if (id == -ENOENT)
- fill->devices[fill->cur].devid = VFIO_PCI_DEVID_OWNED;
+ info.devid = VFIO_PCI_DEVID_OWNED;
else
- fill->devices[fill->cur].devid = VFIO_PCI_DEVID_NOT_OWNED;
+ info.devid = VFIO_PCI_DEVID_NOT_OWNED;
}
/* If devid is VFIO_PCI_DEVID_NOT_OWNED, clear owned flag. */
- if (fill->devices[fill->cur].devid == VFIO_PCI_DEVID_NOT_OWNED)
+ if (info.devid == VFIO_PCI_DEVID_NOT_OWNED)
fill->flags &= ~VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED;
} else {
struct iommu_group *iommu_group;
@@ -823,13 +829,13 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
if (!iommu_group)
return -EPERM; /* Cannot reset non-isolated devices */
- fill->devices[fill->cur].group_id = iommu_group_id(iommu_group);
+ info.group_id = iommu_group_id(iommu_group);
iommu_group_put(iommu_group);
}
- fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus);
- fill->devices[fill->cur].bus = pdev->bus->number;
- fill->devices[fill->cur].devfn = pdev->devfn;
- fill->cur++;
+
+ if (copy_to_user(fill->devices, &info, sizeof(info)))
+ return -EFAULT;
+ fill->devices++;
return 0;
}
@@ -1221,8 +1227,7 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
unsigned long minsz =
offsetofend(struct vfio_pci_hot_reset_info, count);
struct vfio_pci_hot_reset_info hdr;
- struct vfio_pci_fill_info fill = { 0 };
- struct vfio_pci_dependent_device *devices = NULL;
+ struct vfio_pci_fill_info fill = {};
bool slot = false;
int ret = 0;
@@ -1240,29 +1245,9 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
else if (pci_probe_reset_bus(vdev->pdev->bus))
return -ENODEV;
- /* How many devices are affected? */
- ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
- &fill.max, slot);
- if (ret)
- return ret;
-
- WARN_ON(!fill.max); /* Should always be at least one */
-
- /*
- * If there's enough space, fill it now, otherwise return -ENOSPC and
- * the number of devices affected.
- */
- if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) {
- ret = -ENOSPC;
- hdr.count = fill.max;
- goto reset_info_exit;
- }
-
- devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL);
- if (!devices)
- return -ENOMEM;
-
- fill.devices = devices;
+ fill.devices = arg->devices;
+ fill.devices_end = arg->devices +
+ (hdr.argsz - sizeof(hdr)) / sizeof(arg->devices[0]);
fill.vdev = &vdev->vdev;
if (vfio_device_cdev_opened(&vdev->vdev))
@@ -1273,29 +1258,17 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_fill_devs,
&fill, slot);
mutex_unlock(&vdev->vdev.dev_set->lock);
+ if (ret)
+ return ret;
- /*
- * If a device was removed between counting and filling, we may come up
- * short of fill.max. If a device was added, we'll have a return of
- * -EAGAIN above.
- */
- if (!ret) {
- hdr.count = fill.cur;
- hdr.flags = fill.flags;
- }
-
-reset_info_exit:
+ hdr.count = fill.count;
+ hdr.flags = fill.flags;
if (copy_to_user(arg, &hdr, minsz))
- ret = -EFAULT;
-
- if (!ret) {
- if (copy_to_user(&arg->devices, devices,
- hdr.count * sizeof(*devices)))
- ret = -EFAULT;
- }
+ return -EFAULT;
- kfree(devices);
- return ret;
+ if (fill.count != fill.devices - arg->devices)
+ return -ENOSPC;
+ return 0;
}
static int
--
2.34.1
next prev parent reply other threads:[~2023-06-16 9:31 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-16 9:30 [PATCH v8 00/10] Enhance vfio PCI hot reset for vfio cdev device Yi Liu
2023-06-16 9:30 ` [PATCH v8 01/10] vfio/pci: Update comment around group_fd get in vfio_pci_ioctl_pci_hot_reset() Yi Liu
2023-06-16 9:30 ` [PATCH v8 02/10] vfio/pci: Move the existing hot reset logic to be a helper Yi Liu
2023-06-16 9:30 ` [PATCH v8 03/10] iommufd: Reserve all negative IDs in the iommufd xarray Yi Liu
2023-06-16 9:30 ` [PATCH v8 04/10] iommufd: Add iommufd_ctx_has_group() Yi Liu
2023-06-16 9:30 ` [PATCH v8 05/10] iommufd: Add helper to retrieve iommufd_ctx and devid Yi Liu
2023-06-16 9:30 ` [PATCH v8 06/10] vfio: Mark cdev usage in vfio_device Yi Liu
2023-06-16 9:30 ` [PATCH v8 07/10] vfio: Add helper to search vfio_device in a dev_set Yi Liu
2023-06-16 9:30 ` [PATCH v8 08/10] vfio/pci: Extend VFIO_DEVICE_GET_PCI_HOT_RESET_INFO for vfio device cdev Yi Liu
2023-06-22 15:22 ` Jason Gunthorpe
2023-06-16 9:30 ` Yi Liu [this message]
2023-06-16 9:30 ` [PATCH v8 10/10] vfio/pci: Allow passing zero-length fd array in VFIO_DEVICE_PCI_HOT_RESET Yi Liu
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=20230616093042.65094-10-yi.l.liu@intel.com \
--to=yi.l.liu@intel.com \
--cc=alex.williamson@redhat.com \
--cc=chao.p.peng@linux.intel.com \
--cc=clegoate@redhat.com \
--cc=cohuck@redhat.com \
--cc=eric.auger@redhat.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-gvt-dev@lists.freedesktop.org \
--cc=jasowang@redhat.com \
--cc=jgg@nvidia.com \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=lulu@redhat.com \
--cc=mjrosato@linux.ibm.com \
--cc=nicolinc@nvidia.com \
--cc=peterx@redhat.com \
--cc=robin.murphy@arm.com \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=suravee.suthikulpanit@amd.com \
--cc=terrence.xu@intel.com \
--cc=xudong.hao@intel.com \
--cc=yan.y.zhao@intel.com \
--cc=yanting.jiang@intel.com \
--cc=yi.y.sun@linux.intel.com \
--cc=zhenzhong.duan@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