From: Gal Pressman <gal@nvidia.com>
To: "David S. Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>
Cc: David Ahern <dsahern@gmail.com>,
Stephen Hemminger <stephen@networkplumber.org>,
Michal Kubecek <mkubecek@suse.cz>, <netdev@vger.kernel.org>,
Edwin Peer <edwin.peer@broadcom.com>,
Edwin Peer <espeer@gmail.com>, Gal Pressman <gal@nvidia.com>
Subject: [PATCH net-next] rtnetlink: extend RTEXT_FILTER_SKIP_STATS to IFLA_VF_INFO
Date: Sun, 11 Jun 2023 13:51:08 +0300 [thread overview]
Message-ID: <20230611105108.122586-1-gal@nvidia.com> (raw)
From: Edwin Peer <edwin.peer@broadcom.com>
This filter already exists for excluding IPv6 SNMP stats. Extend its
definition to also exclude IFLA_VF_INFO stats in RTM_GETLINK.
This patch constitutes a partial fix for a netlink attribute nesting
overflow bug in IFLA_VFINFO_LIST. By excluding the stats when the
requester doesn't need them, the truncation of the VF list is avoided.
While it was technically only the stats added in commit c5a9f6f0ab40
("net/core: Add drop counters to VF statistics") breaking the camel's
back, the appreciable size of the stats data should never have been
included without due consideration for the maximum number of VFs
supported by PCI.
Fixes: 3b766cd83232 ("net/core: Add reading VF statistics through the PF netdevice")
Fixes: c5a9f6f0ab40 ("net/core: Add drop counters to VF statistics")
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Cc: Edwin Peer <espeer@gmail.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
---
Following our discussion in:
https://lore.kernel.org/netdev/20230607093324.2b7712d9@kernel.org/
I've rebased and testesd this single patch by Edwin.
It is only a partial "fix", but increases the number of VFs presented
before the truncation occurs.
---
net/core/rtnetlink.c | 96 +++++++++++++++++++++++---------------------
1 file changed, 51 insertions(+), 45 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 41de3a2f29e1..d1815122298d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -961,24 +961,27 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
nla_total_size(sizeof(struct ifla_vf_rate)) +
nla_total_size(sizeof(struct ifla_vf_link_state)) +
nla_total_size(sizeof(struct ifla_vf_rss_query_en)) +
- nla_total_size(0) + /* nest IFLA_VF_STATS */
- /* IFLA_VF_STATS_RX_PACKETS */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_TX_PACKETS */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_RX_BYTES */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_TX_BYTES */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_BROADCAST */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_MULTICAST */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_RX_DROPPED */
- nla_total_size_64bit(sizeof(__u64)) +
- /* IFLA_VF_STATS_TX_DROPPED */
- nla_total_size_64bit(sizeof(__u64)) +
nla_total_size(sizeof(struct ifla_vf_trust)));
+ if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) {
+ size += num_vfs *
+ (nla_total_size(0) + /* nest IFLA_VF_STATS */
+ /* IFLA_VF_STATS_RX_PACKETS */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_PACKETS */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_RX_BYTES */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_BYTES */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_BROADCAST */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_MULTICAST */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_RX_DROPPED */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* IFLA_VF_STATS_TX_DROPPED */
+ nla_total_size_64bit(sizeof(__u64)));
+ }
return size;
} else
return 0;
@@ -1270,7 +1273,8 @@ static noinline_for_stack int rtnl_fill_stats(struct sk_buff *skb,
static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
struct net_device *dev,
int vfs_num,
- struct nlattr *vfinfo)
+ struct nlattr *vfinfo,
+ u32 ext_filter_mask)
{
struct ifla_vf_rss_query_en vf_rss_query_en;
struct nlattr *vf, *vfstats, *vfvlanlist;
@@ -1376,33 +1380,35 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
goto nla_put_vf_failure;
}
nla_nest_end(skb, vfvlanlist);
- memset(&vf_stats, 0, sizeof(vf_stats));
- if (dev->netdev_ops->ndo_get_vf_stats)
- dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
- &vf_stats);
- vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS);
- if (!vfstats)
- goto nla_put_vf_failure;
- if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
- vf_stats.rx_packets, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS,
- vf_stats.tx_packets, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES,
- vf_stats.rx_bytes, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES,
- vf_stats.tx_bytes, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
- vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
- vf_stats.multicast, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED,
- vf_stats.rx_dropped, IFLA_VF_STATS_PAD) ||
- nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED,
- vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) {
- nla_nest_cancel(skb, vfstats);
- goto nla_put_vf_failure;
+ if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) {
+ memset(&vf_stats, 0, sizeof(vf_stats));
+ if (dev->netdev_ops->ndo_get_vf_stats)
+ dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
+ &vf_stats);
+ vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS);
+ if (!vfstats)
+ goto nla_put_vf_failure;
+ if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
+ vf_stats.rx_packets, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_PACKETS,
+ vf_stats.tx_packets, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_BYTES,
+ vf_stats.rx_bytes, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_BYTES,
+ vf_stats.tx_bytes, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_BROADCAST,
+ vf_stats.broadcast, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_MULTICAST,
+ vf_stats.multicast, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_DROPPED,
+ vf_stats.rx_dropped, IFLA_VF_STATS_PAD) ||
+ nla_put_u64_64bit(skb, IFLA_VF_STATS_TX_DROPPED,
+ vf_stats.tx_dropped, IFLA_VF_STATS_PAD)) {
+ nla_nest_cancel(skb, vfstats);
+ goto nla_put_vf_failure;
+ }
+ nla_nest_end(skb, vfstats);
}
- nla_nest_end(skb, vfstats);
nla_nest_end(skb, vf);
return 0;
@@ -1435,7 +1441,7 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
return -EMSGSIZE;
for (i = 0; i < num_vfs; i++) {
- if (rtnl_fill_vfinfo(skb, dev, i, vfinfo))
+ if (rtnl_fill_vfinfo(skb, dev, i, vfinfo, ext_filter_mask))
return -EMSGSIZE;
}
--
2.39.1
next reply other threads:[~2023-06-11 10:51 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-11 10:51 Gal Pressman [this message]
2023-06-11 15:06 ` [PATCH net-next] rtnetlink: extend RTEXT_FILTER_SKIP_STATS to IFLA_VF_INFO Stephen Hemminger
2023-06-11 17:58 ` Gal Pressman
2023-06-12 5:34 ` Keller, Jacob E
2023-06-14 9:03 ` Paolo Abeni
2023-06-14 15:17 ` David Ahern
2023-06-14 16:39 ` Jakub Kicinski
2023-06-14 13:20 ` patchwork-bot+netdevbpf
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=20230611105108.122586-1-gal@nvidia.com \
--to=gal@nvidia.com \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=edwin.peer@broadcom.com \
--cc=espeer@gmail.com \
--cc=kuba@kernel.org \
--cc=mkubecek@suse.cz \
--cc=netdev@vger.kernel.org \
--cc=stephen@networkplumber.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.