Re: [PATCH net v2] net/mlx5: free mlx5_st_idx_data on final dealloc

[Paolo Abeni <pabeni@redhat.com>]

On 7/13/26 10:08 AM, Leon Romanovsky wrote:
> On Fri, Jul 10, 2026 at 01:25:45PM +0200, Paolo Abeni wrote:
>> On 7/3/26 12:24 AM, Zhiping Zhang wrote:
>>> Workloads that repeatedly allocate and release mkeys carrying TPH
>>> steering-tag hints (e.g. churning RDMA MRs) leak one
>>> struct mlx5_st_idx_data per cycle; kmemleak flags it as unreferenced
>>> and the kmalloc slab grows over time.
>>>
>>> When the last reference to an ST table entry is dropped,
>>> mlx5_st_dealloc_index() removed the entry from idx_xa but the backing
>>> mlx5_st_idx_data allocation was never freed.
>>>
>>> Free idx_data after the xa_erase() so the lifetime of the bookkeeping
>>> struct matches the lifetime of the ST entry it tracks.
>>>
>>> Cc: stable@vger.kernel.org
>>> Fixes: 888a7776f4fb ("net/mlx5: Add support for device steering tag")
>>> Reviewed-by: Michael Gur <michaelgur@nvidia.com>
>>> Signed-off-by: Zhiping Zhang <zhipingz@meta.com>
>> @Leon, @Saeed, @Tariq: just in case this fell under the radar, it's
>> waiting for your ack.
> 
> Tariq and I completed this on Jul 5 and Jul 6.
> 
> https://lore.kernel.org/linux-rdma/20260705141920.GI15188@unreal/
> https://lore.kernel.org/linux-rdma/0bb37f75-c94a-4a10-b115-186b71daf14f@nvidia.com/
Thank you for pointing out and for the review. PW lost track of it,
likely because there are multiple copies of the same patch/revision and
only one of them landed on the netdev ML.

Applying right now.

/P