Commit 0886196c authored by Jason Gunthorpe's avatar Jason Gunthorpe Committed by Alex Williamson
Browse files

vfio: Use GFP_KERNEL_ACCOUNT for userspace persistent allocations 



Use GFP_KERNEL_ACCOUNT for userspace persistent allocations.

The GFP_KERNEL_ACCOUNT option lets the memory allocator know that this
is untrusted allocation triggered from userspace and should be a subject
of kmem accounting, and as such it is controlled by the cgroup
mechanism.

The way to find the relevant allocations was for example to look at the
close_device function and trace back all the kfrees to their
allocations.

Signed-off-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Signed-off-by: default avatarYishai Hadas <yishaih@nvidia.com>
Reviewed-by: default avatarJason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20230108154427.32609-4-yishaih@nvidia.com


Signed-off-by: default avatarAlex Williamson <alex.williamson@redhat.com>
parent 83ff6095

drivers/vfio/container.c

+1 −1
Original line number Diff line number Diff line
@@ -367,7 +367,7 @@ static int vfio_fops_open(struct inode *inode, struct file *filep) 
{

	struct vfio_container *container;



	container = kzalloc(sizeof(*container), GFP_KERNEL);

	container = kzalloc(sizeof(*container), GFP_KERNEL_ACCOUNT);

	if (!container)

		return -ENOMEM;

drivers/vfio/pci/vfio_pci_config.c

+3 −3
Original line number Diff line number Diff line
@@ -1244,7 +1244,7 @@ static int vfio_msi_cap_len(struct vfio_pci_core_device *vdev, u8 pos) 
	if (vdev->msi_perm)

		return len;



	vdev->msi_perm = kmalloc(sizeof(struct perm_bits), GFP_KERNEL);

	vdev->msi_perm = kmalloc(sizeof(struct perm_bits), GFP_KERNEL_ACCOUNT);

	if (!vdev->msi_perm)

		return -ENOMEM;
@@ -1731,11 +1731,11 @@ int vfio_config_init(struct vfio_pci_core_device *vdev) 
	 * no requirements on the length of a capability, so the gap between

	 * capabilities needs byte granularity.

	 */

	map = kmalloc(pdev->cfg_size, GFP_KERNEL);

	map = kmalloc(pdev->cfg_size, GFP_KERNEL_ACCOUNT);

	if (!map)

		return -ENOMEM;



	vconfig = kmalloc(pdev->cfg_size, GFP_KERNEL);

	vconfig = kmalloc(pdev->cfg_size, GFP_KERNEL_ACCOUNT);

	if (!vconfig) {

		kfree(map);

		return -ENOMEM;

drivers/vfio/pci/vfio_pci_core.c

+4 −3
Original line number Diff line number Diff line
@@ -144,7 +144,8 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_core_device *vdev) 
			 * of the exclusive page in case that hot-add

			 * device's bar is assigned into it.

			 */

			dummy_res = kzalloc(sizeof(*dummy_res), GFP_KERNEL);

			dummy_res =

				kzalloc(sizeof(*dummy_res), GFP_KERNEL_ACCOUNT);

			if (dummy_res == NULL)

				goto no_mmap;
@@ -863,7 +864,7 @@ int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, 


	region = krealloc(vdev->region,

			  (vdev->num_regions + 1) * sizeof(*region),

			  GFP_KERNEL);

			  GFP_KERNEL_ACCOUNT);

	if (!region)

		return -ENOMEM;
@@ -1644,7 +1645,7 @@ static int __vfio_pci_add_vma(struct vfio_pci_core_device *vdev, 
{

	struct vfio_pci_mmap_vma *mmap_vma;



	mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL);

	mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL_ACCOUNT);

	if (!mmap_vma)

		return -ENOMEM;

drivers/vfio/pci/vfio_pci_igd.c

+1 −1
Original line number Diff line number Diff line
@@ -180,7 +180,7 @@ static int vfio_pci_igd_opregion_init(struct vfio_pci_core_device *vdev) 
	if (!addr || !(~addr))

		return -ENODEV;



	opregionvbt = kzalloc(sizeof(*opregionvbt), GFP_KERNEL);

	opregionvbt = kzalloc(sizeof(*opregionvbt), GFP_KERNEL_ACCOUNT);

	if (!opregionvbt)

		return -ENOMEM;

drivers/vfio/pci/vfio_pci_intrs.c

+6 −4
Original line number Diff line number Diff line
@@ -177,7 +177,7 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev) 
	if (!vdev->pdev->irq)

		return -ENODEV;



	vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);

	vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL_ACCOUNT);

	if (!vdev->ctx)

		return -ENOMEM;
@@ -216,7 +216,7 @@ static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, int fd) 
	if (fd < 0) /* Disable only */

		return 0;



	vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)",

	vdev->ctx[0].name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)",

				      pci_name(pdev));

	if (!vdev->ctx[0].name)

		return -ENOMEM;
@@ -284,7 +284,8 @@ static int vfio_msi_enable(struct vfio_pci_core_device *vdev, int nvec, bool msi 
	if (!is_irq_none(vdev))

		return -EINVAL;



	vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);

	vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx),

			    GFP_KERNEL_ACCOUNT);

	if (!vdev->ctx)

		return -ENOMEM;
@@ -343,7 +344,8 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev, 
	if (fd < 0)

		return 0;



	vdev->ctx[vector].name = kasprintf(GFP_KERNEL, "vfio-msi%s[%d](%s)",

	vdev->ctx[vector].name = kasprintf(GFP_KERNEL_ACCOUNT,

					   "vfio-msi%s[%d](%s)",

					   msix ? "x" : "", vector,

					   pci_name(pdev));

	if (!vdev->ctx[vector].name)