* [PATCH v2] vhost: account the per-device kernel allocations to memcg
@ 2026-11-20 5:45 Tao Cui
2026-11-20 5:49 ` sashiko-bot
2026-11-20 20:47 ` Bobby Eshleman
0 siblings, 2 replies; 3+ messages in thread
From: Tao Cui @ 2026-11-20 5:45 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Jason Wang, Eugenio Pérez, Stefan Hajnoczi,
Stefano Garzarella, Bobby Eshleman, Andrey Drobyshev,
virtualization, kvm, linux-mm, akpm, cuitao, cui.tao
From: Tao Cui <cuitao@kylinos.cn>
Everything except the worker struct is allocated with plain GFP_KERNEL:
the per-vq iovec and log arrays at VHOST_SET_OWNER, the memory table at
VHOST_SET_MEM_TABLE whose size follows the user supplied region count,
the pending message nodes, and the vhost_net/vhost_vsock device structs
with their fallback to vmalloc. The worker has been accounted since the
vhost_task conversion.
A container that can open /dev/vhost-net or /dev/vhost-vsock, which
device plugins hand out with passthrough, holds roughly 150KB of
resident kernel memory per device after SET_OWNER. Charge the rest the
same way the worker already is.
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Tao Cui <cuitao@kylinos.cn>
---
Changes in v2:
- rebased on next-20261118, where the vq->nheads allocation now uses
kmalloc_objs(); the flag addition follows the new form. No
functional change. Carries Michael's Acked-by from v1.
Link to v1: https://lore.kernel.org/r/20261106131829.3228926-4-cui.tao@linux.dev
drivers/vhost/net.c | 14 ++++++++------
drivers/vhost/vhost.c | 17 +++++++++++------
drivers/vhost/vsock.c | 5 +++--
3 files changed, 22 insertions(+), 14 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 435d8ed3851f..390858056d20 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -249,7 +249,7 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
/* No zero copy backend? Nothing to count. */
if (!zcopy)
return NULL;
- ubufs = kmalloc_obj(*ubufs);
+ ubufs = kmalloc_obj(*ubufs, GFP_KERNEL_ACCOUNT);
if (!ubufs)
return ERR_PTR(-ENOMEM);
atomic_set(&ubufs->refcount, 1);
@@ -302,7 +302,8 @@ static int vhost_net_set_ubuf_info(struct vhost_net *n)
if (!zcopy)
continue;
n->vqs[i].ubuf_info =
- kmalloc_objs(*n->vqs[i].ubuf_info, UIO_MAXIOV);
+ kmalloc_objs(*n->vqs[i].ubuf_info, UIO_MAXIOV,
+ GFP_KERNEL_ACCOUNT);
if (!n->vqs[i].ubuf_info)
goto err;
}
@@ -1340,17 +1341,18 @@ static int vhost_net_open(struct inode *inode, struct file *f)
struct xdp_buff *xdp;
int i;
- n = kvmalloc_obj(*n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
+ n = kvmalloc_obj(*n, GFP_KERNEL | __GFP_RETRY_MAYFAIL |
+ __GFP_ACCOUNT);
if (!n)
return -ENOMEM;
- vqs = kmalloc_objs(*vqs, VHOST_NET_VQ_MAX);
+ vqs = kmalloc_objs(*vqs, VHOST_NET_VQ_MAX, GFP_KERNEL_ACCOUNT);
if (!vqs) {
kvfree(n);
return -ENOMEM;
}
queue = kmalloc_array(VHOST_NET_BATCH, sizeof(void *),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!queue) {
kfree(vqs);
kvfree(n);
@@ -1358,7 +1360,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
}
n->vqs[VHOST_NET_VQ_RX].rxq.queue = queue;
- xdp = kmalloc_objs(*xdp, VHOST_NET_BATCH);
+ xdp = kmalloc_objs(*xdp, VHOST_NET_BATCH, GFP_KERNEL_ACCOUNT);
if (!xdp) {
kfree(vqs);
kvfree(n);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index dc973287567c..e8f9dce52aa7 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -526,10 +526,14 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
for (i = 0; i < dev->nvqs; ++i) {
vq = dev->vqs[i];
- vq->indirect = kmalloc_objs(*vq->indirect, UIO_MAXIOV);
- vq->log = kmalloc_objs(*vq->log, dev->iov_limit);
- vq->heads = kmalloc_objs(*vq->heads, dev->iov_limit);
- vq->nheads = kmalloc_objs(*vq->nheads, dev->iov_limit);
+ vq->indirect = kmalloc_objs(*vq->indirect, UIO_MAXIOV,
+ GFP_KERNEL_ACCOUNT);
+ vq->log = kmalloc_objs(*vq->log, dev->iov_limit,
+ GFP_KERNEL_ACCOUNT);
+ vq->heads = kmalloc_objs(*vq->heads, dev->iov_limit,
+ GFP_KERNEL_ACCOUNT);
+ vq->nheads = kmalloc_objs(*vq->nheads, dev->iov_limit,
+ GFP_KERNEL_ACCOUNT);
if (!vq->indirect || !vq->log || !vq->heads || !vq->nheads)
goto err_nomem;
}
@@ -2052,7 +2056,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
return -E2BIG;
if (max_iotlb_entries <= 0)
return -EINVAL;
- newmem = kvzalloc_flex(*newmem, regions, mem.nregions);
+ newmem = kvzalloc_flex(*newmem, regions, mem.nregions,
+ GFP_KERNEL_ACCOUNT);
if (!newmem)
return -ENOMEM;
@@ -3407,7 +3412,7 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify);
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
{
/* Make sure all padding within the structure is initialized. */
- struct vhost_msg_node *node = kzalloc_obj(*node);
+ struct vhost_msg_node *node = kzalloc_obj(*node, GFP_KERNEL_ACCOUNT);
if (!node)
return NULL;
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 88a310390eb0..2fa205967f8a 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -719,11 +719,12 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
/* This struct is large and allocation could fail, fall back to vmalloc
* if there is no other way.
*/
- vsock = kvmalloc_obj(*vsock, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
+ vsock = kvmalloc_obj(*vsock, GFP_KERNEL | __GFP_RETRY_MAYFAIL |
+ __GFP_ACCOUNT);
if (!vsock)
return -ENOMEM;
- vqs = kmalloc_objs(*vqs, ARRAY_SIZE(vsock->vqs));
+ vqs = kmalloc_objs(*vqs, ARRAY_SIZE(vsock->vqs), GFP_KERNEL_ACCOUNT);
if (!vqs) {
ret = -ENOMEM;
goto out;
--
2.53.0
^ permalink raw reply related [flat|nested] 3+ messages in thread* Re: [PATCH v2] vhost: account the per-device kernel allocations to memcg
2026-11-20 5:45 [PATCH v2] vhost: account the per-device kernel allocations to memcg Tao Cui
@ 2026-11-20 5:49 ` sashiko-bot
2026-11-20 20:47 ` Bobby Eshleman
1 sibling, 0 replies; 3+ messages in thread
From: sashiko-bot @ 2026-11-20 5:49 UTC (permalink / raw)
To: Tao Cui; +Cc: virtualization, Michael S. Tsirkin, Eugenio Perez
> From: Tao Cui <cuitao@kylinos.cn>
>
> Everything except the worker struct is allocated with plain GFP_KERNEL:
> the per-vq iovec and log arrays at VHOST_SET_OWNER, the memory table at
> VHOST_SET_MEM_TABLE whose size follows the user supplied region count,
> the pending message nodes, and the vhost_net/vhost_vsock device structs
> with their fallback to vmalloc. The worker has been accounted since the
> vhost_task conversion.
>
> A container that can open /dev/vhost-net or /dev/vhost-vsock, which
> device plugins hand out with passthrough, holds roughly 150KB of
> resident kernel memory per device after SET_OWNER. Charge the rest the
> same way the worker already is.
>
> Acked-by: Michael S. Tsirkin <mst@redhat.com>
> Signed-off-by: Tao Cui <cuitao@kylinos.cn>
Sashiko has reviewed this patch and found no issues.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20261120054517.526275-1-cui.tao@linux.dev?part=1
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH v2] vhost: account the per-device kernel allocations to memcg
2026-11-20 5:45 [PATCH v2] vhost: account the per-device kernel allocations to memcg Tao Cui
2026-11-20 5:49 ` sashiko-bot
@ 2026-11-20 20:47 ` Bobby Eshleman
1 sibling, 0 replies; 3+ messages in thread
From: Bobby Eshleman @ 2026-11-20 20:47 UTC (permalink / raw)
To: Tao Cui
Cc: Michael S. Tsirkin, Jason Wang, Eugenio Pérez,
Stefan Hajnoczi, Stefano Garzarella, Andrey Drobyshev,
virtualization, kvm, linux-mm, akpm, cuitao
On Fri, Nov 20, 2026 at 01:45:17PM +0800, Tao Cui wrote:
> From: Tao Cui <cuitao@kylinos.cn>
>
> Everything except the worker struct is allocated with plain GFP_KERNEL:
> the per-vq iovec and log arrays at VHOST_SET_OWNER, the memory table at
> VHOST_SET_MEM_TABLE whose size follows the user supplied region count,
> the pending message nodes, and the vhost_net/vhost_vsock device structs
> with their fallback to vmalloc. The worker has been accounted since the
> vhost_task conversion.
>
> A container that can open /dev/vhost-net or /dev/vhost-vsock, which
> device plugins hand out with passthrough, holds roughly 150KB of
> resident kernel memory per device after SET_OWNER. Charge the rest the
> same way the worker already is.
>
> Acked-by: Michael S. Tsirkin <mst@redhat.com>
> Signed-off-by: Tao Cui <cuitao@kylinos.cn>
> ---
> Changes in v2:
> - rebased on next-20261118, where the vq->nheads allocation now uses
> kmalloc_objs(); the flag addition follows the new form. No
> functional change. Carries Michael's Acked-by from v1.
> Link to v1: https://lore.kernel.org/r/20261106131829.3228926-4-cui.tao@linux.dev
>
> drivers/vhost/net.c | 14 ++++++++------
> drivers/vhost/vhost.c | 17 +++++++++++------
> drivers/vhost/vsock.c | 5 +++--
> 3 files changed, 22 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 435d8ed3851f..390858056d20 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -249,7 +249,7 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
> /* No zero copy backend? Nothing to count. */
> if (!zcopy)
> return NULL;
> - ubufs = kmalloc_obj(*ubufs);
> + ubufs = kmalloc_obj(*ubufs, GFP_KERNEL_ACCOUNT);
> if (!ubufs)
> return ERR_PTR(-ENOMEM);
> atomic_set(&ubufs->refcount, 1);
> @@ -302,7 +302,8 @@ static int vhost_net_set_ubuf_info(struct vhost_net *n)
> if (!zcopy)
> continue;
> n->vqs[i].ubuf_info =
> - kmalloc_objs(*n->vqs[i].ubuf_info, UIO_MAXIOV);
> + kmalloc_objs(*n->vqs[i].ubuf_info, UIO_MAXIOV,
> + GFP_KERNEL_ACCOUNT);
> if (!n->vqs[i].ubuf_info)
> goto err;
> }
> @@ -1340,17 +1341,18 @@ static int vhost_net_open(struct inode *inode, struct file *f)
> struct xdp_buff *xdp;
> int i;
>
> - n = kvmalloc_obj(*n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
> + n = kvmalloc_obj(*n, GFP_KERNEL | __GFP_RETRY_MAYFAIL |
> + __GFP_ACCOUNT);
> if (!n)
> return -ENOMEM;
> - vqs = kmalloc_objs(*vqs, VHOST_NET_VQ_MAX);
> + vqs = kmalloc_objs(*vqs, VHOST_NET_VQ_MAX, GFP_KERNEL_ACCOUNT);
> if (!vqs) {
> kvfree(n);
> return -ENOMEM;
> }
>
> queue = kmalloc_array(VHOST_NET_BATCH, sizeof(void *),
> - GFP_KERNEL);
> + GFP_KERNEL_ACCOUNT);
> if (!queue) {
> kfree(vqs);
> kvfree(n);
> @@ -1358,7 +1360,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
> }
> n->vqs[VHOST_NET_VQ_RX].rxq.queue = queue;
>
> - xdp = kmalloc_objs(*xdp, VHOST_NET_BATCH);
> + xdp = kmalloc_objs(*xdp, VHOST_NET_BATCH, GFP_KERNEL_ACCOUNT);
> if (!xdp) {
> kfree(vqs);
> kvfree(n);
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index dc973287567c..e8f9dce52aa7 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -526,10 +526,14 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
>
> for (i = 0; i < dev->nvqs; ++i) {
> vq = dev->vqs[i];
> - vq->indirect = kmalloc_objs(*vq->indirect, UIO_MAXIOV);
> - vq->log = kmalloc_objs(*vq->log, dev->iov_limit);
> - vq->heads = kmalloc_objs(*vq->heads, dev->iov_limit);
> - vq->nheads = kmalloc_objs(*vq->nheads, dev->iov_limit);
> + vq->indirect = kmalloc_objs(*vq->indirect, UIO_MAXIOV,
> + GFP_KERNEL_ACCOUNT);
> + vq->log = kmalloc_objs(*vq->log, dev->iov_limit,
> + GFP_KERNEL_ACCOUNT);
> + vq->heads = kmalloc_objs(*vq->heads, dev->iov_limit,
> + GFP_KERNEL_ACCOUNT);
> + vq->nheads = kmalloc_objs(*vq->nheads, dev->iov_limit,
> + GFP_KERNEL_ACCOUNT);
> if (!vq->indirect || !vq->log || !vq->heads || !vq->nheads)
> goto err_nomem;
> }
> @@ -2052,7 +2056,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
> return -E2BIG;
> if (max_iotlb_entries <= 0)
> return -EINVAL;
> - newmem = kvzalloc_flex(*newmem, regions, mem.nregions);
> + newmem = kvzalloc_flex(*newmem, regions, mem.nregions,
> + GFP_KERNEL_ACCOUNT);
> if (!newmem)
> return -ENOMEM;
>
> @@ -3407,7 +3412,7 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify);
> struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
> {
> /* Make sure all padding within the structure is initialized. */
> - struct vhost_msg_node *node = kzalloc_obj(*node);
> + struct vhost_msg_node *node = kzalloc_obj(*node, GFP_KERNEL_ACCOUNT);
> if (!node)
> return NULL;
>
> diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
> index 88a310390eb0..2fa205967f8a 100644
> --- a/drivers/vhost/vsock.c
> +++ b/drivers/vhost/vsock.c
> @@ -719,11 +719,12 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
> /* This struct is large and allocation could fail, fall back to vmalloc
> * if there is no other way.
> */
> - vsock = kvmalloc_obj(*vsock, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
> + vsock = kvmalloc_obj(*vsock, GFP_KERNEL | __GFP_RETRY_MAYFAIL |
> + __GFP_ACCOUNT);
> if (!vsock)
> return -ENOMEM;
>
> - vqs = kmalloc_objs(*vqs, ARRAY_SIZE(vsock->vqs));
> + vqs = kmalloc_objs(*vqs, ARRAY_SIZE(vsock->vqs), GFP_KERNEL_ACCOUNT);
> if (!vqs) {
> ret = -ENOMEM;
> goto out;
> --
> 2.53.0
>
The vsock bits look good to me!
Acked-by: Bobby Eshleman <bobbyeshleman@meta.com>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-11-20 20:47 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-20 5:45 [PATCH v2] vhost: account the per-device kernel allocations to memcg Tao Cui
2026-11-20 5:49 ` sashiko-bot
2026-11-20 20:47 ` Bobby Eshleman
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox