* [PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify()
@ 2026-01-13 11:41 Jan Vaclav
2026-01-14 18:47 ` Stephen Hemminger
2026-01-14 19:00 ` patchwork-bot+netdevbpf
0 siblings, 2 replies; 3+ messages in thread
From: Jan Vaclav @ 2026-01-13 11:41 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev, Jan Vaclav, Gris Ge
The expected size for IFLA_INFO_KIND in kernel is strlen(kind) + 1.
See `size` in rtnl_link_get_size() in net/core/rtnetlink.c.
Fixes: 1d93483985f0 ("iplink: use netlink for link configuration")
Reported-by: Gris Ge <fge@redhat.com>
Signed-off-by: Jan Vaclav <jvaclav@redhat.com>
---
ip/iplink.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/ip/iplink.c b/ip/iplink.c
index 59e8caf4..fce6631d 100644
--- a/ip/iplink.c
+++ b/ip/iplink.c
@@ -1139,7 +1139,7 @@ static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type,
- strlen(type));
+ strlen(type) + 1);
lu = get_link_kind(type);
if (ulinep && !strcmp(ulinep, "_slave"))
--
2.51.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify()
2026-01-13 11:41 [PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify() Jan Vaclav
@ 2026-01-14 18:47 ` Stephen Hemminger
2026-01-14 19:00 ` patchwork-bot+netdevbpf
1 sibling, 0 replies; 3+ messages in thread
From: Stephen Hemminger @ 2026-01-14 18:47 UTC (permalink / raw)
To: Jan Vaclav; +Cc: netdev, Gris Ge
On Tue, 13 Jan 2026 12:41:27 +0100
Jan Vaclav <jvaclav@redhat.com> wrote:
> The expected size for IFLA_INFO_KIND in kernel is strlen(kind) + 1.
> See `size` in rtnl_link_get_size() in net/core/rtnetlink.c.
>
> Fixes: 1d93483985f0 ("iplink: use netlink for link configuration")
> Reported-by: Gris Ge <fge@redhat.com>
> Signed-off-by: Jan Vaclav <jvaclav@redhat.com>
> ---
Good catch.
It does raise the issue why IFLA_ALIAS is a binary attribute.
FYI - AI code review agrees.
I'll review this patch by examining all three files you've provided.Now let me provide my review based on the analysis.
---
## Patch Review: `[PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify()`
**Verdict: Patch is correct and should be applied.**
### Analysis
The patch changes:
```c
addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type,
- strlen(type));
+ strlen(type) + 1);
```
This is the right fix. Here's why:
**1. Kernel Policy Requires NLA_STRING**
In `rtnetlink.c:2264`:
```c
[IFLA_INFO_KIND] = { .type = NLA_STRING },
```
The `NLA_STRING` type expects a null-terminated string. The netlink validation layer checks that the last byte is `'\0'`.
**2. Kernel Size Calculation Includes Null Terminator**
In `rtnetlink.c:730` (`rtnl_link_get_size()`):
```c
nla_total_size(strlen(ops->kind) + 1); /* IFLA_INFO_KIND */
```
The kernel explicitly accounts for `strlen + 1` when calculating buffer sizes for outbound messages.
**3. Kernel Uses `nla_put_string()` for Outbound**
In `rtnetlink.c:889`:
```c
nla_put_string(skb, IFLA_INFO_KIND, ops->kind)
```
`nla_put_string()` includes the null terminator, so kernel-to-userspace messages include it.
**4. Why It Worked Before (Probably)**
The current code likely "works" by accident due to netlink's 4-byte alignment requirements. When `addattr_l()` adds an attribute, padding bytes are typically zeroed. For most type strings, the padding happens to provide the null terminator. But this is unreliable:
- If `strlen(type) % 4 == 0`, no padding is added
- Different `addattr_l` implementations may not zero padding
**5. Contrast with IFLA_IFALIAS**
Interestingly, `IFLA_IFALIAS` at line 796-797 also uses `strlen()` without `+1`, but that's actually correct because the kernel explicitly treats it as `NLA_BINARY` (see `rtnetlink.c:2218-2221`) and uses `nla_len()` directly rather than relying on null termination.
### Minor Comment
The commit message is good - it correctly references the kernel source and includes proper tags. One small enhancement might be to note that this has worked by luck due to alignment padding, but that's optional.
**Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>**
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify()
2026-01-13 11:41 [PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify() Jan Vaclav
2026-01-14 18:47 ` Stephen Hemminger
@ 2026-01-14 19:00 ` patchwork-bot+netdevbpf
1 sibling, 0 replies; 3+ messages in thread
From: patchwork-bot+netdevbpf @ 2026-01-14 19:00 UTC (permalink / raw)
To: Jan Vaclav; +Cc: stephen, netdev, fge
Hello:
This patch was applied to iproute2/iproute2.git (main)
by Stephen Hemminger <stephen@networkplumber.org>:
On Tue, 13 Jan 2026 12:41:27 +0100 you wrote:
> The expected size for IFLA_INFO_KIND in kernel is strlen(kind) + 1.
> See `size` in rtnl_link_get_size() in net/core/rtnetlink.c.
>
> Fixes: 1d93483985f0 ("iplink: use netlink for link configuration")
> Reported-by: Gris Ge <fge@redhat.com>
> Signed-off-by: Jan Vaclav <jvaclav@redhat.com>
>
> [...]
Here is the summary with links:
- [iproute2] ip/iplink: fix off-by-one KIND length in modify()
https://git.kernel.org/pub/scm/network/iproute2/iproute2.git/commit/?id=683815ed61ed
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-01-14 19:03 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-01-13 11:41 [PATCH iproute2] ip/iplink: fix off-by-one KIND length in modify() Jan Vaclav
2026-01-14 18:47 ` Stephen Hemminger
2026-01-14 19:00 ` patchwork-bot+netdevbpf
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox