In the Linux kernel, the following vulnerability has been resolved:

net: ethernet: ti: am65-cpsw: fix freeing IRQ in am65_cpsw_nuss_remove_tx_chns()

When getting the IRQ we use k3_udma_glue_tx_get_irq() which returns
negative error value on error. So not NULL check is not sufficient
to deteremine if IRQ is valid. Check that IRQ is greater then zero
to ensure it is valid.

There is no issue at probe time but at runtime user can invoke
.set_channels which results in the following call chain.
am65_cpsw_set_channels()
 am65_cpsw_nuss_update_tx_rx_chns()
  am65_cpsw_nuss_remove_tx_chns()
  am65_cpsw_nuss_init_tx_chns()

At this point if am65_cpsw_nuss_init_tx_chns() fails due to
k3_udma_glue_tx_get_irq() then tx_chn->irq will be set to a
negative value.

Then, at subsequent .set_channels with higher channel count we
will attempt to free an invalid IRQ in am65_cpsw_nuss_remove_tx_chns()
leading to a kernel warning.

The issue is present in the original commit that introduced this driver,
although there, am65_cpsw_nuss_update_tx_rx_chns() existed as
am65_cpsw_nuss_update_tx_chns().

https://git.kernel.org/stable/c/4395a44acb15850e492dd1de9ec4b6479d96bc80

https://git.kernel.org/stable/c/8448c87b3af68bebca21e3136913f7f77e363515

https://git.kernel.org/stable/c/88fd5db8c0073bd91d18391feb5741aeb0a2b475

https://git.kernel.org/stable/c/8aae91ae1c65782a169ec070e023d4d269e5d6e6

https://git.kernel.org/stable/c/aea5cca681d268f794fa2385f9ec26a5cce025cd