| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20251118165659-mutt-send-email-mst@kernel.org>
Date: Tue, 18 Nov 2025 17:06:57 -0500
From: "Michael S. Tsirkin" <mst@...hat.com>
To: Daniel Jurgens <danielj@...dia.com>
Cc: netdev@...r.kernel.org, jasowang@...hat.com, pabeni@...hat.com,
virtualization@...ts.linux.dev, parav@...dia.com,
shshitrit@...dia.com, yohadt@...dia.com, xuanzhuo@...ux.alibaba.com,
eperezma@...hat.com, jgg@...pe.ca, kevin.tian@...el.com,
kuba@...nel.org, andrew+netdev@...n.ch, edumazet@...gle.com
Subject: Re: [PATCH net-next v11 05/12] virtio_net: Query and set flow filter
caps
On Tue, Nov 18, 2025 at 08:38:55AM -0600, Daniel Jurgens wrote:
> When probing a virtnet device, attempt to read the flow filter
> capabilities. In order to use the feature the caps must also
> be set. For now setting what was read is sufficient.
>
> Signed-off-by: Daniel Jurgens <danielj@...dia.com>
> Reviewed-by: Parav Pandit <parav@...dia.com>
> Reviewed-by: Shahar Shitrit <shshitrit@...dia.com>
>
> ---
> v4:
> - Validate the length in the selector caps
> - Removed __free usage.
> - Removed for(int.
> v5:
> - Remove unneed () after MAX_SEL_LEN macro (test bot)
> v6:
> - Fix sparse warning "array of flexible structures" Jakub K/Simon H
> - Use new variable and validate ff_mask_size before set_cap. MST
> v7:
> - Set ff->ff_{caps, mask, actions} NULL in error path. Paolo Abeni
> - Return errors from virtnet_ff_init, -ENOTSUPP is not fatal. Xuan
>
> v8:
> - Use real_ff_mask_size when setting the selector caps. Jason Wang
>
> v9:
> - Set err after failed memory allocations. Simon Horman
>
> v10:
> - Return -EOPNOTSUPP in virnet_ff_init before allocing any memory.
> Jason/Paolo.
>
> v11:
> - Return -EINVAL if any resource limit is 0. Simon Horman
> - Ensure we don't overrun alloced space of ff->ff_mask by moving the
> real_ff_mask_size > ff_mask_size check into the loop. Simon Horman
> ---
> drivers/net/virtio_net.c | 201 +++++++++++++++++++++++++++++
> include/linux/virtio_admin.h | 1 +
> include/uapi/linux/virtio_net_ff.h | 91 +++++++++++++
> 3 files changed, 293 insertions(+)
> create mode 100644 include/uapi/linux/virtio_net_ff.h
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index cfa006b88688..3615f45ac358 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -26,6 +26,9 @@
> #include <net/netdev_rx_queue.h>
> #include <net/netdev_queues.h>
> #include <net/xdp_sock_drv.h>
> +#include <linux/virtio_admin.h>
> +#include <net/ipv6.h>
> +#include <net/ip.h>
>
> static int napi_weight = NAPI_POLL_WEIGHT;
> module_param(napi_weight, int, 0444);
> @@ -281,6 +284,14 @@ static const struct virtnet_stat_desc virtnet_stats_tx_speed_desc_qstat[] = {
> VIRTNET_STATS_DESC_TX_QSTAT(speed, ratelimit_packets, hw_drop_ratelimits),
> };
>
> +struct virtnet_ff {
> + struct virtio_device *vdev;
> + bool ff_supported;
> + struct virtio_net_ff_cap_data *ff_caps;
> + struct virtio_net_ff_cap_mask_data *ff_mask;
> + struct virtio_net_ff_actions *ff_actions;
> +};
> +
> #define VIRTNET_Q_TYPE_RX 0
> #define VIRTNET_Q_TYPE_TX 1
> #define VIRTNET_Q_TYPE_CQ 2
> @@ -493,6 +504,8 @@ struct virtnet_info {
> struct failover *failover;
>
> u64 device_stats_cap;
> +
> + struct virtnet_ff ff;
> };
>
> struct padded_vnet_hdr {
> @@ -6774,6 +6787,183 @@ static const struct xdp_metadata_ops virtnet_xdp_metadata_ops = {
> .xmo_rx_hash = virtnet_xdp_rx_hash,
> };
>
> +static size_t get_mask_size(u16 type)
> +{
> + switch (type) {
> + case VIRTIO_NET_FF_MASK_TYPE_ETH:
> + return sizeof(struct ethhdr);
> + case VIRTIO_NET_FF_MASK_TYPE_IPV4:
> + return sizeof(struct iphdr);
> + case VIRTIO_NET_FF_MASK_TYPE_IPV6:
> + return sizeof(struct ipv6hdr);
> + case VIRTIO_NET_FF_MASK_TYPE_TCP:
> + return sizeof(struct tcphdr);
> + case VIRTIO_NET_FF_MASK_TYPE_UDP:
> + return sizeof(struct udphdr);
> + }
> +
> + return 0;
> +}
> +
> +#define MAX_SEL_LEN (sizeof(struct ipv6hdr))
> +
> +static int virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev)
> +{
> + size_t ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data) +
> + sizeof(struct virtio_net_ff_selector) *
> + VIRTIO_NET_FF_MASK_TYPE_MAX;
> + struct virtio_admin_cmd_query_cap_id_result *cap_id_list;
> + struct virtio_net_ff_selector *sel;
> + size_t real_ff_mask_size;
> + int err;
> + int i;
> +
> + if (!vdev->config->admin_cmd_exec)
> + return -EOPNOTSUPP;
> +
> + cap_id_list = kzalloc(sizeof(*cap_id_list), GFP_KERNEL);
> + if (!cap_id_list)
> + return -ENOMEM;
> +
> + err = virtio_admin_cap_id_list_query(vdev, cap_id_list);
> + if (err)
> + goto err_cap_list;
> +
> + if (!(VIRTIO_CAP_IN_LIST(cap_id_list,
> + VIRTIO_NET_FF_RESOURCE_CAP) &&
> + VIRTIO_CAP_IN_LIST(cap_id_list,
> + VIRTIO_NET_FF_SELECTOR_CAP) &&
> + VIRTIO_CAP_IN_LIST(cap_id_list,
> + VIRTIO_NET_FF_ACTION_CAP))) {
> + err = -EOPNOTSUPP;
> + goto err_cap_list;
> + }
> +
> + ff->ff_caps = kzalloc(sizeof(*ff->ff_caps), GFP_KERNEL);
> + if (!ff->ff_caps) {
> + err = -ENOMEM;
> + goto err_cap_list;
> + }
> +
> + err = virtio_admin_cap_get(vdev,
> + VIRTIO_NET_FF_RESOURCE_CAP,
> + ff->ff_caps,
> + sizeof(*ff->ff_caps));
> +
> + if (err)
> + goto err_ff;
> +
> + if (!ff->ff_caps->groups_limit ||
> + !ff->ff_caps->classifiers_limit ||
> + !ff->ff_caps->rules_limit ||
> + !ff->ff_caps->rules_per_group_limit) {
> + err = -EINVAL;
> + goto err_ff;
> + }
> +
> + /* VIRTIO_NET_FF_MASK_TYPE start at 1 */
> + for (i = 1; i <= VIRTIO_NET_FF_MASK_TYPE_MAX; i++)
> + ff_mask_size += get_mask_size(i);
> +
> + ff->ff_mask = kzalloc(ff_mask_size, GFP_KERNEL);
> + if (!ff->ff_mask) {
> + err = -ENOMEM;
> + goto err_ff;
> + }
> +
> + err = virtio_admin_cap_get(vdev,
> + VIRTIO_NET_FF_SELECTOR_CAP,
> + ff->ff_mask,
> + ff_mask_size);
> +
> + if (err)
> + goto err_ff_mask;
> +
> + ff->ff_actions = kzalloc(sizeof(*ff->ff_actions) +
> + VIRTIO_NET_FF_ACTION_MAX,
> + GFP_KERNEL);
> + if (!ff->ff_actions) {
> + err = -ENOMEM;
> + goto err_ff_mask;
> + }
> +
> + err = virtio_admin_cap_get(vdev,
> + VIRTIO_NET_FF_ACTION_CAP,
> + ff->ff_actions,
> + sizeof(*ff->ff_actions) + VIRTIO_NET_FF_ACTION_MAX);
> +
> + if (err)
> + goto err_ff_action;
> +
> + err = virtio_admin_cap_set(vdev,
> + VIRTIO_NET_FF_RESOURCE_CAP,
> + ff->ff_caps,
> + sizeof(*ff->ff_caps));
> + if (err)
> + goto err_ff_action;
> +
> + real_ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data);
> + sel = (void *)&ff->ff_mask->selectors[0];
why the cast? discards type checks for no good reason I can see.
And &...[0] is unnecessarily funky. Just plain ff->ff_mask->selectors
will do.
> +
> + for (i = 0; i < ff->ff_mask->count; i++) {
> + if (sel->length > MAX_SEL_LEN) {
> + err = -EINVAL;
> + goto err_ff_action;
> + }
> + real_ff_mask_size += sizeof(struct virtio_net_ff_selector) + sel->length;
> + if (real_ff_mask_size > ff_mask_size) {
> + err = -EINVAL;
> + goto err_ff_action;
> + }
> + sel = (void *)sel + sizeof(*sel) + sel->length;
I guess the MAX_SEL_LEN check guarantees the allocation
is big enough? Let's add a BUG_ON just in case.
> + }
> +
> + err = virtio_admin_cap_set(vdev,
> + VIRTIO_NET_FF_SELECTOR_CAP,
> + ff->ff_mask,
> + real_ff_mask_size);
> + if (err)
> + goto err_ff_action;
> +
> + err = virtio_admin_cap_set(vdev,
> + VIRTIO_NET_FF_ACTION_CAP,
> + ff->ff_actions,
> + sizeof(*ff->ff_actions) + VIRTIO_NET_FF_ACTION_MAX);
> + if (err)
> + goto err_ff_action;
> +
> + ff->vdev = vdev;
> + ff->ff_supported = true;
> +
> + kfree(cap_id_list);
> +
> + return 0;
> +
> +err_ff_action:
> + kfree(ff->ff_actions);
> + ff->ff_actions = NULL;
> +err_ff_mask:
> + kfree(ff->ff_mask);
> + ff->ff_mask = NULL;
> +err_ff:
> + kfree(ff->ff_caps);
> + ff->ff_caps = NULL;
> +err_cap_list:
> + kfree(cap_id_list);
> +
> + return err;
> +}
> +
> +static void virtnet_ff_cleanup(struct virtnet_ff *ff)
> +{
> + if (!ff->ff_supported)
> + return;
> +
> + kfree(ff->ff_actions);
> + kfree(ff->ff_mask);
> + kfree(ff->ff_caps);
> +}
> +
> static int virtnet_probe(struct virtio_device *vdev)
> {
> int i, err = -ENOMEM;
> @@ -7137,6 +7327,15 @@ static int virtnet_probe(struct virtio_device *vdev)
> }
> vi->guest_offloads_capable = vi->guest_offloads;
>
> + /* Initialize flow filters. Not supported is an acceptable and common
> + * return code
> + */
> + err = virtnet_ff_init(&vi->ff, vi->vdev);
> + if (err && err != -EOPNOTSUPP) {
> + rtnl_unlock();
> + goto free_unregister_netdev;
> + }
> +
> rtnl_unlock();
>
> err = virtnet_cpu_notif_add(vi);
> @@ -7152,6 +7351,7 @@ static int virtnet_probe(struct virtio_device *vdev)
>
> free_unregister_netdev:
> unregister_netdev(dev);
> + virtnet_ff_cleanup(&vi->ff);
> free_failover:
> net_failover_destroy(vi->failover);
> free_vqs:
> @@ -7201,6 +7401,7 @@ static void virtnet_remove(struct virtio_device *vdev)
> virtnet_free_irq_moder(vi);
>
> unregister_netdev(vi->dev);
> + virtnet_ff_cleanup(&vi->ff);
>
> net_failover_destroy(vi->failover);
>
> diff --git a/include/linux/virtio_admin.h b/include/linux/virtio_admin.h
> index 039b996f73ec..db0f42346ca9 100644
> --- a/include/linux/virtio_admin.h
> +++ b/include/linux/virtio_admin.h
> @@ -3,6 +3,7 @@
> * Header file for virtio admin operations
> */
> #include <uapi/linux/virtio_pci.h>
> +#include <uapi/linux/virtio_net_ff.h>
>
> #ifndef _LINUX_VIRTIO_ADMIN_H
> #define _LINUX_VIRTIO_ADMIN_H
Why do it? Let net pull this header itself.
> diff --git a/include/uapi/linux/virtio_net_ff.h b/include/uapi/linux/virtio_net_ff.h
> new file mode 100644
> index 000000000000..bd7a194a9959
> --- /dev/null
> +++ b/include/uapi/linux/virtio_net_ff.h
you should document in commit log that you are adding
these types to UAPI, and which spec they are from.
> @@ -0,0 +1,91 @@
> +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
> + *
> + * Header file for virtio_net flow filters
> + */
> +#ifndef _LINUX_VIRTIO_NET_FF_H
> +#define _LINUX_VIRTIO_NET_FF_H
> +
> +#include <linux/types.h>
> +#include <linux/kernel.h>
> +
> +#define VIRTIO_NET_FF_RESOURCE_CAP 0x800
> +#define VIRTIO_NET_FF_SELECTOR_CAP 0x801
> +#define VIRTIO_NET_FF_ACTION_CAP 0x802
> +
> +/**
> + * struct virtio_net_ff_cap_data - Flow filter resource capability limits
> + * @groups_limit: maximum number of flow filter groups supported by the device
> + * @classifiers_limit: maximum number of classifiers supported by the device
> + * @rules_limit: maximum number of rules supported device-wide across all groups
> + * @rules_per_group_limit: maximum number of rules allowed in a single group
> + * @last_rule_priority: priority value associated with the lowest-priority rule
> + * @selectors_per_classifier_limit: maximum selectors allowed in one classifier
> + *
> + * The limits are reported by the device and describe resource capacities for
> + * flow filters. Multi-byte fields are little-endian.
> + */
> +struct virtio_net_ff_cap_data {
> + __le32 groups_limit;
> + __le32 classifiers_limit;
> + __le32 rules_limit;
> + __le32 rules_per_group_limit;
> + __u8 last_rule_priority;
> + __u8 selectors_per_classifier_limit;
Ouch this is a problem. There is a 2 byte padding here.
This is a spec bug but I don't know if it is too late to fix.
Parav what do you think?
> +};
> +
> +/**
> + * struct virtio_net_ff_selector - Selector mask descriptor
> + * @type: selector type, one of VIRTIO_NET_FF_MASK_TYPE_* constants
> + * @flags: selector flags, see VIRTIO_NET_FF_MASK_F_* constants
> + * @reserved: must be set to 0 by the driver and ignored by the device
> + * @length: size in bytes of @mask
> + * @reserved1: must be set to 0 by the driver and ignored by the device
> + * @mask: variable-length mask payload for @type, length given by @length
> + *
> + * A selector describes a header mask that a classifier can apply. The format
> + * of @mask depends on @type.
> + */
> +struct virtio_net_ff_selector {
> + __u8 type;
> + __u8 flags;
> + __u8 reserved[2];
> + __u8 length;
> + __u8 reserved1[3];
> + __u8 mask[];
> +};
> +
> +#define VIRTIO_NET_FF_MASK_TYPE_ETH 1
> +#define VIRTIO_NET_FF_MASK_TYPE_IPV4 2
> +#define VIRTIO_NET_FF_MASK_TYPE_IPV6 3
> +#define VIRTIO_NET_FF_MASK_TYPE_TCP 4
> +#define VIRTIO_NET_FF_MASK_TYPE_UDP 5
> +#define VIRTIO_NET_FF_MASK_TYPE_MAX VIRTIO_NET_FF_MASK_TYPE_UDP
> +
> +/**
> + * struct virtio_net_ff_cap_mask_data - Supported selector mask formats
> + * @count: number of entries in @selectors
> + * @reserved: must be set to 0 by the driver and ignored by the device
> + * @selectors: array of supported selector descriptors
> + */
> +struct virtio_net_ff_cap_mask_data {
> + __u8 count;
> + __u8 reserved[7];
> + __u8 selectors[];
> +};
> +#define VIRTIO_NET_FF_MASK_F_PARTIAL_MASK (1 << 0)
> +
> +#define VIRTIO_NET_FF_ACTION_DROP 1
> +#define VIRTIO_NET_FF_ACTION_RX_VQ 2
> +#define VIRTIO_NET_FF_ACTION_MAX VIRTIO_NET_FF_ACTION_RX_VQ
> +/**
> + * struct virtio_net_ff_actions - Supported flow actions
> + * @count: number of supported actions in @actions
> + * @reserved: must be set to 0 by the driver and ignored by the device
> + * @actions: array of action identifiers (VIRTIO_NET_FF_ACTION_*)
> + */
> +struct virtio_net_ff_actions {
> + __u8 count;
> + __u8 reserved[7];
> + __u8 actions[];
> +};
> +#endif
> --
> 2.50.1
Powered by blists - more mailing lists