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: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20230108154427.32609-4-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

7 files changed, 17 insertions, 14 deletions

diff --git a/drivers/vfio/container.c b/drivers/vfio/container.c
index b7a9560ab25e..5f398c493a1b 100644
--- a/drivers/vfio/container.c
+++ b/drivers/vfio/container.c
@@ -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;
 
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index 4a350421c5f6..523e0144c86f 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -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;
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 26a541cc64d1..a6492a25ff6a 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -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;
 
diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c
index 5e6ca5926954..dd70e2431bd7 100644
--- a/drivers/vfio/pci/vfio_pci_igd.c
+++ b/drivers/vfio/pci/vfio_pci_igd.c
@@ -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;
 
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 40c3d7cf163f..bffb0741518b 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -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)
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index e352a033b4ae..e27de61ac9fe 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -470,7 +470,7 @@ int vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset,
 		goto out_unlock;
 	}
 
-	ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL);
+	ioeventfd = kzalloc(sizeof(*ioeventfd), GFP_KERNEL_ACCOUNT);
 	if (!ioeventfd) {
 		ret = -ENOMEM;
 		goto out_unlock;
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 497a17b37865..29c564b7a6e1 100644
--- a/drivers/vfio/virqfd.c
+++ b/drivers/vfio/virqfd.c
@@ -112,7 +112,7 @@ int vfio_virqfd_enable(void *opaque,
 	int ret = 0;
 	__poll_t events;
 
-	virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
+	virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL_ACCOUNT);
 	if (!virqfd)
 		return -ENOMEM;